Radeon RX 9070 XT vs NVIDIA H200 (SXM)
Radeon RX 9070 XT
Advanced Micro Devices, Inc.
Radeon RX 9070 XT wins · 12–5 (10 drawn)
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
Agent access
ai-native userPoint an agent at llms.txt or agent-oriented docs
weight 2 · round to Radeon RX 9070 XTA direct probe confirms rocm.docs.amd.com/llms.txt returns HTTP 200 with structured content pointing to sub-project docs, giving an agent a genuine machine-readable entry point into the Radeon/ROCm software docs relevant to this GPU. Missing for 10: no evidence of llms.txt coverage at finer granularity (e.g., per-page) and no OpenAPI/agent API surface (which 404s), so agentic doc access is present but not comprehensive.
- [probe] “PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple pro…”
- [probe] “PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.am…”
- [claimed-docs] “PyTorch on Windows updated with ROCm 7.2.1 on AMD Radeon graphics products and AMD Ryzen AI processors.”
A probe confirms developer.nvidia.com/llms.txt returns HTTP 200 with a real summary, showing NVIDIA does expose an agent-readable entry point for its developer docs, but this is a generic portal file, not specific to H200 GPU documentation, and other agent-friendly formats (docs.md, OpenAPI) return 404s. Missing for 10: H200-specific machine-readable docs, working docs.md/OpenAPI endpoints, and confirmation an agent can navigate beyond the root llms.txt.
- [probe] “PROBE llms.txt: HTTP 200 at https://developer.nvidia.com/llms.txt # NVIDIA Developer > Comprehensive developer portal for NVIDIA accelerate…”
- [probe] “PROBE docs-md: HTTP 404 at https://developer.nvidia.com/cuda-toolkit.md”
- [probe] “PROBE openapi: all candidate paths 404 (https://developer.nvidia.com/openapi.json, https://developer.nvidia.com/swagger.json, https://develo…”
ai-native userRun the product headlessly / in CI for automation
weight 2 · round to Radeon RX 9070 XTEvidence shows ROCm/Linux support with PyTorch, vLLM, and Llama.cpp for compute workloads (amd-rx-9070-xt-docs-2, -10, -11), which implies the GPU can be used for automated inference/training pipelines without a display, but there is no explicit documentation of headless operation, Docker/CI runner support, or automation-specific tooling. Missing for 10: explicit headless-mode docs, CI/container integration guides, and any hands-on evidence of running in automated pipelines.
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “OS Support Windows 10 - 64-Bit Edition , Windows 11 - 64-Bit Edition , Linux x86 64-Bit”
ai-native userUse an official CLI
weight 2 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
ai-native userDrive the product through a documented public API
weight 3 · round to Radeon RX 9070 XTAMD documents a public software stack (ROCm) with APIs/libraries (HIP, PyTorch/TensorFlow/JAX/ONNX/vLLM/llama.cpp integration) that let developers programmatically drive the GPU for AI workloads, and llms.txt is served for documentation discovery. However, there is no dedicated machine-callable REST/OpenAPI interface — the openapi probe returned 404 on all candidate paths — so an AI agent cannot invoke a structured public API directly, only use ROCm's compiled libraries/frameworks. Missing for 10: a documented REST/OpenAPI or similarly agent-consumable API endpoint, independent confirmation of programmatic control beyond framework bindings.
- [claimed-docs] “PyTorch on Windows updated with ROCm 7.2.1 on AMD Radeon graphics products and AMD Ryzen AI processors.”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [probe] “PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple pro…”
- [probe] “PROBE openapi: all candidate paths 404 (https://rocm.docs.amd.com/openapi.json, https://rocm.docs.amd.com/swagger.json, https://rocm.docs.am…”
NVIDIA H200 (SXM)none0/10The H200 is a hardware accelerator; while CUDA Toolkit and Nsight tools provide programming interfaces, there is no evidence of a documented public REST/agentic API for driving the product, and explicit probes for OpenAPI/swagger specs all returned 404s.
ai-native userBuild against official SDKs
weight 2 · round to Radeon RX 9070 XTAMD provides official ROCm SDK documentation for the RX 9070 XT enabling development with PyTorch, TensorFlow, JAX, ONNX, vLLM, and llama.cpp on both Windows and Linux, with an llms.txt confirming machine-readable docs availability. Missing for 10: independent hands-on developer confirmation of SDK stability/completeness, and no evidence of API/openapi endpoints for programmatic integration.
- [claimed-docs] “PyTorch on Windows updated with ROCm 7.2.1 on AMD Radeon graphics products and AMD Ryzen AI processors.”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Windows® PyTorch”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “The same ROCm™ stack that powers your desktop development on RDNA™ architecture GPUs also supports AMD Instinct™ accelerators on CDNA™ archi…”
- [probe] “PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple pro…”
NVIDIA provides official SDKs to build against (CUDA Toolkit, Nsight developer tools, and NIM microservices bundled via NVIDIA AI Enterprise) that target the H200 hardware, and a developer portal exists with an llms.txt discovery file. However, probes show no machine-readable docs (404 on .md) and no OpenAPI/swagger spec, and there's no H200-specific agentic SDK evidence beyond generic CUDA/NIM tooling. missing for 10: agent-specific SDK examples, machine-readable API docs (docs-md returned 404), OpenAPI spec availability, independent developer corroboration of SDK usability for AI-native/agentic workflows.
- [claimed-docs] “NVIDIA AI Enterprise includes NVIDIA NIM™, a set of easy-to-use microservices designed to speed up enterprise generative AI deployment.”
- [claimed-docs] “With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data …”
- [claimed-docs] “NVIDIA Nsight Compute and Nsight System suite of tools designed to help developers optimize and increase performance of their applications.”
- [probe] “PROBE llms.txt: HTTP 200 at https://developer.nvidia.com/llms.txt # NVIDIA Developer > Comprehensive developer portal for NVIDIA accelerate…”
- [probe] “PROBE docs-md: HTTP 404 at https://developer.nvidia.com/cuda-toolkit.md”
- [probe] “PROBE openapi: all candidate paths 404 (https://developer.nvidia.com/openapi.json, https://developer.nvidia.com/swagger.json, https://develo…”
Agentic features
ai-native userGet AI-generated insights and suggestions from my data inside the product
weight 2 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
ai-native userDelegate tasks to a built-in AI assistant inside the product
weight 3 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
ai-native userOperate the product with natural-language commands
weight 2 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
Ai compute — stories about ai compute in this arenaAi compute
Stories about ai compute in this arena
Inference stack
ai-native userThis GPU has a documented LLM inference story — low-precision formats (FP8/FP4) and supported serving stacks (TensorRT-LLM, vLLM, ROCm, llama.cpp) for this part
weight 3 · round to Radeon RX 9070 XTROCm docs explicitly document serving-stack support for this Radeon line (vLLM 'Full support', llama.cpp 'Supported for efficient inference', plus PyTorch/TensorFlow/JAX/ONNX), but there is no mention of low-precision FP8/FP4 inference formats for the RX 9070 XT, and TensorRT-LLM is an NVIDIA-only stack so is not applicable here. Missing for 10: explicit FP8/FP4 quantization support documentation for this card, independent hands-on benchmarks confirming these serving stacks actually run well on RX 9070 XT.
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Windows® PyTorch”
NVIDIA docs and runtime probes confirm H200's HBM3e specs and FP8 tensor performance figures, and community evidence shows real-world LLM inference (Llama2, Llama 405B) throughput gains, but no evidence names FP4 support or specific serving-stack integration (TensorRT-LLM, vLLM, ROCm, llama.cpp) for this part. missing for 10: explicit FP4 precision docs, named serving-stack support (TensorRT-LLM/vLLM/ROCm/llama.cpp) tied to H200.
- [claimed-docs] “The H200 boosts inference speed by up to 2X compared to H100 GPUs when handling LLMs like Llama2.”
- [claimed-docs] “the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s)”
- [community] “Llama 405B up to 142 tok/s on Nvidia H200 SXM — launched a production grade API endpoint at $3 per million tokens, made possible by H200 SXM…”
- [probe] “PROBE runtime (recorded 2026-09-15): NVIDIA's H200 datacenter page answered a keyless curl and names the part — the spec table (141GB HBM3e,…”
Tensor specs
ml engineerSize training and inference from published tensor throughput — TFLOPS or TOPS with precision and sparsity stated, not a bare marketing number
weight 3 · round to NVIDIA H200 (SXM)Radeon RX 9070 XTnone0/10The evidence pack covers ROCm software support, framework compatibility, and general features, but contains no published TFLOPS/TOPS figures for the RX 9070 XT with precision (FP16/FP32/INT8) or sparsity stated. Missing for 10: any tensor throughput numbers, precision breakdown, sparsity conditions, or comparison to a baseline needed for training/inference sizing.
- [claimed-docs] “OS Support Windows 10 - 64-Bit Edition , Windows 11 - 64-Bit Edition , Linux x86 64-Bit”
- [claimed-docs] “AV1 Decode Yes AV1 Encode Yes”
NVIDIA's H200 page is confirmed live and does contain a spec table with FP8 tensor figures and bandwidth/capacity numbers (per probe-rt-1), but the evidence pack itself surfaces mostly bare marketing multipliers ('2X faster than H100', '110X faster than CPU') rather than the actual precision-tagged TFLOPS/TOPS figures with sparsity conditions spelled out. Community commentary also notes the H200 reuses H100 silicon, adding skepticism to headline comparisons rather than to the raw spec numbers themselves. Missing for 10: explicit quoted TFLOPS/TOPS values per precision (FP8/FP16/INT8) with dense vs. sparse figures, and independent benchmark corroboration of those specific numbers.
- [claimed-docs] “The H200 boosts inference speed by up to 2X compared to H100 GPUs when handling LLMs like Llama2.”
- [claimed-docs] “the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s)”
- [probe] “PROBE runtime (recorded 2026-09-15): NVIDIA's H200 datacenter page answered a keyless curl and names the part — the spec table (141GB HBM3e,…”
- [community] “The H200 GPU die is the same as the H100, but it's using a full set of faster 24GB memory stacks... This is an H100 141GB, not new silicon l…”
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
ai-native userPerform bulk operations across many items at once
weight 2 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
ai-native userSchedule recurring jobs or workflows
weight 2 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
Creator media — stories about creator media in this arenaCreator media
Stories about creator media in this arena
Media engines
creatorHardware media engines and creator-app acceleration are documented — AV1/HEVC encoders, and professional or ISV-certified driver support where the vendor claims it
weight 2 · round to Radeon RX 9070 XTAMD's product page explicitly documents AV1 encode/decode support for the RX 9070 XT, which is relevant to creator workflows, but there is no mention of HEVC encode/decode support, no ISV-certified professional driver program (that's typically reserved for Radeon Pro cards), and no explicit creator-app acceleration claims (e.g., Premiere, DaVinci Resolve, OBS integration). Missing for 10: HEVC encoder/decoder documentation, ISV/professional certification claims, named creator-app acceleration partnerships or benchmarks.
- [claimed-docs] “AV1 Decode Yes AV1 Encode Yes”
Datacenter scale — stories about datacenter scale in this arenaDatacenter scale
Stories about datacenter scale in this arena
Scale out
ml engineerTrain and serve at datacenter scale on this part — documented high-bandwidth interconnect (NVLink, Infinity Fabric), multi-GPU systems, and rack-scale deployment
weight 3 · round to NVIDIA H200 (SXM)Radeon RX 9070 XTnone0/10The evidence only shows ROCm software compatibility and a vague note that the same stack 'also supports' Instinct/CDNA datacenter accelerators, but nothing documents NVLink/Infinity Fabric interconnect, multi-GPU scaling, or rack-scale deployment for the RX 9070 XT itself, which is a single consumer desktop card without such interconnects. missing for 10: any documentation of multi-GPU interconnect (NVLink/Infinity Fabric) for this card, multi-GPU system support, rack-scale deployment guidance.
- [claimed-docs] “The same ROCm™ stack that powers your desktop development on RDNA™ architecture GPUs also supports AMD Instinct™ accelerators on CDNA™ archi…”
- [claimed-docs] “This unified platform creates a seamless migration path, allowing you to develop applications locally and deploy them at scale with confiden…”
Evidence confirms the SXM form factor, MIG partitioning, CUDA toolkit for datacenter deployment, and community proof of real multi-GPU serving (Llama 405B at 142 tok/s across H200 SXMs) validating datacenter-scale operation, but the pack never cites NVLink/NVSwitch bandwidth figures, Infinity Fabric, or DGX/HGX rack-scale system specs that the story explicitly asks for. missing for 10: explicit NVLink/NVSwitch bandwidth numbers, DGX/HGX rack-scale system documentation, independent rack-scale benchmark corroboration.
- [claimed-docs] “the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s)”
- [claimed-docs] “Multi-Instance GPUs Up to 7 MIGs @18GB each”
- [community] “Llama 405B up to 142 tok/s on Nvidia H200 SXM — launched a production grade API endpoint at $3 per million tokens, made possible by H200 SXM…”
- [claimed-docs] “With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data …”
Driver openness — stories about driver openness in this arenaDriver openness
Stories about driver openness in this arena
Linux support
developerLinux is a first-class citizen for this GPU — documented Linux driver releases and independent Linux testing of this part
weight 2 · round to Radeon RX 9070 XTAMD's official docs explicitly list Linux x86-64 as a supported OS and provide detailed ROCm Linux documentation for PyTorch/TensorFlow/JAX/ONNX, vLLM, and llama.cpp on Radeon 9000-series GPUs, showing genuine first-class Linux driver/software support. However, the pack lacks independent hands-on Linux testing or benchmarks of the RX 9070 XT specifically (the only community citation is a general Windows-oriented performance review, not Linux-focused). Missing for 10: independent/third-party Linux driver stability or performance testing of this specific card, and any community confirmation of ROCm functionality on this GPU outside vendor docs.
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “OS Support Windows 10 - 64-Bit Edition , Windows 11 - 64-Bit Edition , Linux x86 64-Bit”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “As a primarily open-source ecosystem, ROCm™ gives you the freedom to inspect, customize, and tailor the software stack to your specific need…”
NVIDIA H200 (SXM)none0/10Evidence pack lacks any explicit mention of Linux driver releases, release notes, or independent Linux benchmarking/testing of the H200; CUDA toolkit blurb only vaguely references 'data centers' and 'supercomputers' without naming Linux, and community links focus on inference throughput or die comparisons, not OS-specific testing.
Open drivers
developerRun this GPU on an open driver — open-source kernel modules or upstream Linux support documented by the vendor
weight 2 · round to Radeon RX 9070 XTAMD documents ROCm as a primarily open-source stack with Linux support and lists RX 9000-series compatibility, and Linux x86 64-bit OS support is confirmed, but there is no explicit vendor documentation of open-source kernel driver components (e.g., amdgpu upstream kernel module) specific to RX 9070 XT or a clear statement of which parts of the stack are closed-source firmware/blobs. missing for 10: explicit vendor confirmation of upstream open-source kernel module support for this specific GPU, independent/hands-on corroboration of open driver functioning on mainline Linux kernels.
- [claimed-docs] “As a primarily open-source ecosystem, ROCm™ gives you the freedom to inspect, customize, and tailor the software stack to your specific need…”
- [claimed-docs] “OS Support Windows 10 - 64-Bit Edition , Windows 11 - 64-Bit Edition , Linux x86 64-Bit”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
NVIDIA H200 (SXM)none0/10Evidence shows only proprietary CUDA toolkit and NVIDIA AI Enterprise stack; nothing about open-source kernel modules (nvidia-open) or upstream Linux driver support is documented in the pack. Missing for 10: any mention of NVIDIA's open GPU kernel modules, upstream mainline Linux driver support, or open-source driver documentation for the H200.
- [claimed-docs] “With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data …”
- [claimed-docs] “NVIDIA Nsight Compute and Nsight System suite of tools designed to help developers optimize and increase performance of their applications.”
Gaming performance — stories about gaming performance in this arenaGaming performance
Stories about gaming performance in this arena
4k gaming
gamerThis card drives high-refresh 4K gaming — vendor performance claims corroborated by independent game benchmarks
weight 3 · round to Radeon RX 9070 XTOnly one independent source (TechPowerUp) confirms the RX 9070 XT delivers competitive raster/ray-tracing performance versus similarly priced NVIDIA cards, but it doesn't specifically address 4K high-refresh benchmarks or vendor FPS claims. Missing for 10: explicit vendor 4K/144Hz+ performance claims, detailed independent 4K benchmark numbers across multiple games, and confirmation of sustained high-refresh framerates.
- [community] “The RX 9070 XT offers competitive performance with similarly priced NVIDIA options in both raster and ray tracing, at a starting price of $6…”
Upscaling
gamerAI upscaling and frame generation are supported on this card — the DLSS or FSR generation is documented for this part, with broad game support
weight 2 · round to Radeon RX 9070 XTAMD's product page confirms FSR ("Redstone") support on the RX 9070 XT, and third-party review corroborates strong raster/ray-tracing performance, but the evidence pack lacks detail on frame-generation specifics or a documented list of supported games. missing for 10: explicit frame-generation (FSR 3/4) feature naming, game compatibility list/count, independent hands-on upscaling benchmarks.
- [claimed-docs] “AMD FSR™ "Redstone"”
- [community] “The RX 9070 XT offers competitive performance with similarly priced NVIDIA options in both raster and ray tracing, at a starting price of $6…”
Memory vram — stories about memory vram in this arenaMemory vram
Stories about memory vram in this arena
Llm memory
ai-native userRun a 70B-class quantized LLM on this GPU — published VRAM capacity and memory bandwidth that make local or single-node inference practical
weight 3 · round to NVIDIA H200 (SXM)Radeon RX 9070 XTnone0/10The evidence pack never states the RX 9070 XT's actual VRAM capacity or memory bandwidth; the one VRAM figure mentioned ("up to 48GB") is a generic Radeon workstation-GPU claim, not this card's spec, and there is no claim or benchmark showing a 70B-class quantized model running on this GPU. Software support (ROCm, vLLM, llama.cpp) is documented but doesn't substitute for the missing capacity/bandwidth evidence needed to judge practicality for 70B inference.
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “A local workstation equipped with a Radeon™ GPU, featuring up to 48GB of VRAM, offers a secure and economical alternative to relying solely …”
NVIDIA docs confirm 141GB HBM3e at 4.8TB/s, comfortably fitting a 70B-class quantized model with large batch/context headroom, and this is corroborated by an independent runtime probe and community benchmarks showing real-world inference (e.g., Llama 405B at 142 tok/s) on H200 SXM. Missing for 10: independent hands-on benchmark specifically for a 70B-class quantized model rather than larger models.
- [claimed-docs] “the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s)”
- [community] “Llama 405B up to 142 tok/s on Nvidia H200 SXM — launched a production grade API endpoint at $3 per million tokens, made possible by H200 SXM…”
- [probe] “PROBE runtime (recorded 2026-09-15): NVIDIA's H200 datacenter page answered a keyless curl and names the part — the spec table (141GB HBM3e,…”
Memory spec
ml engineerMemory specs are published in full for this exact part — capacity, memory type, bus width, and bandwidth
weight 2 · round to NVIDIA H200 (SXM)Radeon RX 9070 XTnone0/10Evidence pack contains no VRAM capacity, memory type (GDDR6), bus width, or bandwidth figures for the RX 9070 XT—only ROCm software ecosystem claims and generic product page snippets unrelated to memory specs.
NVIDIA's official H200 page publishes capacity (141GB), memory type (HBM3e), and bandwidth (4.8TB/s), and a runtime probe confirms this spec table is live and fetchable; independent commentary also confirms it's HBM3e stacks on the H100 die. However, memory bus width is never stated anywhere in the evidence pack. Missing for 10: explicit memory bus-width figure, and any independent/third-party spec-sheet corroboration beyond NVIDIA's own page.
- [claimed-docs] “the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s)”
- [probe] “PROBE runtime (recorded 2026-09-15): NVIDIA's H200 datacenter page answered a keyless curl and names the part — the spec table (141GB HBM3e,…”
- [community] “The H200 GPU die is the same as the H100, but it's using a full set of faster 24GB memory stacks... This is an H100 141GB, not new silicon l…”
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
ai-native userRead the product's source under an open license
weight 2 · round to Radeon RX 9070 XTAMD's ROCm docs claim the stack is a 'primarily open-source ecosystem' giving users freedom to inspect and customize the software, and this is corroborated by an accessible llms.txt docs endpoint, but this is the accompanying software stack, not the GPU's actual hardware/firmware source, and 'primarily' implies some closed-source components remain undisclosed. Missing for 10: explicit repository/license pointer for the actual open-sourced source code, confirmation of what portions (drivers, firmware) are closed, and independent hands-on verification of source availability.
- [claimed-docs] “As a primarily open-source ecosystem, ROCm™ gives you the freedom to inspect, customize, and tailor the software stack to your specific need…”
- [probe] “PROBE llms.txt: HTTP 200 at https://rocm.docs.amd.com/llms.txt # ROCm documentation > Note: ROCm documentation is split across multiple pro…”
ai-native userSelf-host the core product
weight 3 · round drawnAs a discrete GPU, the RX 9070 XT is inherently self-hosted hardware; AMD's docs explicitly position a local Radeon workstation as a secure, economical alternative to cloud-based AI solutions, backed by open ROCm stack support for PyTorch/TensorFlow/JAX/ONNX/vLLM/llama.cpp on both Windows and Linux. Missing for 10: independent hands-on validation of a fully self-hosted AI stack setup, and more detailed first-party self-hosting/deployment guides beyond general ROCm docs.
- [claimed-docs] “A local workstation equipped with a Radeon™ GPU, featuring up to 48GB of VRAM, offers a secure and economical alternative to relying solely …”
- [claimed-docs] “This unified platform creates a seamless migration path, allowing you to develop applications locally and deploy them at scale with confiden…”
- [claimed-docs] “The same ROCm™ stack that powers your desktop development on RDNA™ architecture GPUs also supports AMD Instinct™ accelerators on CDNA™ archi…”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
The H200 is physical hardware you purchase/own and deploy in your own datacenter or colo, making self-hosting the core product inherently possible (unlike SaaS AI products), and NVIDIA's stack (CUDA toolkit, drivers, Nsight tools) supports fully on-prem deployment across data centers and workstations. missing for 10: no direct documentation of an on-prem purchase/procurement path or hands-on self-hosting case study, and no independent report confirming ease of self-managed deployment outside of cloud providers.
- [claimed-docs] “With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data …”
- [claimed-docs] “NVIDIA Nsight Compute and Nsight System suite of tools designed to help developers optimize and increase performance of their applications.”
- [claimed-docs] “the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB/s)”
- [community] “Llama 405B up to 142 tok/s on Nvidia H200 SXM — launched a production grade API endpoint at $3 per million tokens, made possible by H200 SXM…”
Power cooling — stories about power cooling in this arenaPower cooling
Stories about power cooling in this arena
Efficiency
ml engineerSustained workloads are power-efficient on this part — documented power envelopes with independent performance-per-watt testing
weight 2 · round to NVIDIA H200 (SXM)Radeon RX 9070 XTnone0/10Evidence covers ROCm software support, framework compatibility, and general GPU features, but there is no documented power envelope data or independent performance-per-watt testing for sustained ML workloads on this card. missing for 10: TDP/power envelope specs for sustained ML loads, independent perf-per-watt benchmarks, thermal/power throttling behavior under long-running compute jobs.
NVIDIA's own docs state the H200 operates 'within the same power profile as the H100' (nvidia-h200-sxm-docs-4), but this is a vendor claim only — no independent performance-per-watt benchmarks or third-party power-envelope testing are present in the evidence pack. Community notes (nvidia-h200-sxm-comm-2) even highlight that H200 shares H100 silicon, which is consistent but not an efficiency benchmark. Missing for 10: independent/hands-on power-draw measurements under sustained load, third-party perf/watt comparisons, and detailed thermal/power documentation beyond the single marketing sentence.
- [claimed-docs] “This cutting-edge technology offers unparalleled performance, all within the same power profile as the H100.”
- [community] “The H200 GPU die is the same as the H100, but it's using a full set of faster 24GB memory stacks... This is an H100 141GB, not new silicon l…”
Psu planning
gamerSpec a build around published board power — TDP/TGP, connector requirements, and cooling guidance for this exact card
weight 2 · round drawnRadeon RX 9070 XTnone0/10The evidence pack covers ROCm/software ecosystem support, AMD Software features, and general performance comparison, but contains no mention of TDP/TGP figures, PCIe power connector requirements, or cooling/case guidance for the RX 9070 XT. This is a fair axis for a discrete GPU, but nothing in the pack substantiates it.
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
ai-native userPrevent my data from being used to train AI models
weight 3 · round drawnRadeon RX 9070 XTnone0/10The axis applies to this product kind (peer products hold positive or none verdicts on this story), so lack of evidence for an applicable capability is "none", never "na". (na/none harmonized at arena bring-up — see pipeline/scripts/na-harmonize.ts.)
Software toolchain — stories about software toolchain in this arenaSoftware toolchain
Stories about software toolchain in this arena
Compute stack
developerShip GPU-compute workloads on the vendor's toolchain — CUDA or ROCm/HIP documentation lists this part as a supported target
weight 3 · round drawnROCm documentation explicitly lists RX 9000 series (including 9070 XT) as a supported target on both Windows and Linux, with PyTorch, TensorFlow, JAX, ONNX, vLLM, and Llama.cpp support, plus a stated migration path to AMD Instinct datacenter GPUs. missing for 10: independent hands-on developer corroboration of ROCm workflows on this specific card beyond vendor docs, and no mention of CUDA compatibility layer maturity/limitations.
- [claimed-docs] “PyTorch on Windows updated with ROCm 7.2.1 on AMD Radeon graphics products and AMD Ryzen AI processors.”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Windows® PyTorch”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “The same ROCm™ stack that powers your desktop development on RDNA™ architecture GPUs also supports AMD Instinct™ accelerators on CDNA™ archi…”
CUDA Toolkit is NVIDIA's standard GPU-compute toolchain, explicitly documented as supporting deployment across data centers and supercomputers, and H200 is the current flagship data-center GPU in this same product family/lineage; community evidence (production LLM inference deployments on H200 SXM) confirms real-world CUDA-based workloads running on this part. Missing for 10: no explicit CUDA compute-capability/architecture list page directly naming 'H200' as a supported gpu-architecture target string, and no ROCm angle (not applicable to NVIDIA anyway).
- [claimed-docs] “With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data …”
- [claimed-docs] “NVIDIA Nsight Compute and Nsight System suite of tools designed to help developers optimize and increase performance of their applications.”
- [community] “Llama 405B up to 142 tok/s on Nvidia H200 SXM — launched a production grade API endpoint at $3 per million tokens, made possible by H200 SXM…”
- [probe] “PROBE runtime (recorded 2026-09-15): NVIDIA's H200 datacenter page answered a keyless curl and names the part — the spec table (141GB HBM3e,…”
Frameworks
ml engineerPyTorch and mainstream ML frameworks run on this GPU through officially documented builds and support matrices
weight 2 · round to Radeon RX 9070 XTAMD's official ROCm docs explicitly list RX 9000 series support for PyTorch (Windows and Linux), TensorFlow, JAX, ONNX, vLLM, and Llama.cpp, with a documented support matrix and OS support (Windows/Linux) confirmed on AMD's product page. Missing for 10: independent hands-on confirmation of install success/version compatibility and no community corroboration of real-world PyTorch training/inference workflows on this specific card.
- [claimed-docs] “PyTorch on Windows updated with ROCm 7.2.1 on AMD Radeon graphics products and AMD Ryzen AI processors.”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Linux® PyTorch, TensorFlow, JAX, ONNX”
- [claimed-docs] “Radeon™ GPUs (9000 & select 7000 Series) Windows® PyTorch”
- [claimed-docs] “**vLLM**: Full support.”
- [claimed-docs] “**Llama.cpp**: Supported for efficient inference.”
- [claimed-docs] “OS Support Windows 10 - 64-Bit Edition , Windows 11 - 64-Bit Edition , Linux x86 64-Bit”
NVIDIA documents CUDA Toolkit support for developing/deploying GPU-accelerated applications and community evidence (HN inference benchmark) shows PyTorch-based LLM workloads (Llama 405B) running in production on H200 SXM, implying framework compatibility via CUDA. However, there is no direct citation of an official PyTorch/TensorFlow support matrix or explicit framework-version compatibility documentation for H200 specifically. Missing for 10: explicit PyTorch/TensorFlow official support matrix naming H200, CUDA/cuDNN version compatibility table, first-party framework installation guide referencing H200.
- [claimed-docs] “With it, you can develop, optimize, and deploy your applications on GPU-accelerated embedded systems, desktop workstations, enterprise data …”
- [claimed-docs] “NVIDIA Nsight Compute and Nsight System suite of tools designed to help developers optimize and increase performance of their applications.”
- [community] “Llama 405B up to 142 tok/s on Nvidia H200 SXM — launched a production grade API endpoint at $3 per million tokens, made possible by H200 SXM…”
Not comparable on these axes
ai-native userPlug MCP servers into this product so it can use their tools
weight 3 · not comparableRadeon RX 9070 XTn/aThe RX 9070 XT is a GPU hardware product, not an agent, app, or platform that could plug in MCP servers; this axis is a category error for a graphics card.
ai-native userConnect an agent via an official MCP server
weight 3 · not comparableRadeon RX 9070 XTn/aThis is a GPU hardware product; MCP server connectivity is a software/agent-role axis unrelated to a graphics card's capabilities, so the story does not apply.
ai-native userIssue scoped/least-privilege API credentials for an agent
weight 2 · not comparableRadeon RX 9070 XTn/aThis story concerns API credential scoping for agent access control, which applies to SaaS/platform services—not a consumer GPU hardware product like the RX 9070 XT. This is a category error/wrong axis for a graphics card.
ai-native userSubscribe to events via webhooks
weight 2 · not comparableRadeon RX 9070 XTn/aThe RX 9070 XT is a GPU hardware product; webhooks/event subscriptions are a software service API concept unrelated to a graphics card's function. This axis is a category error for this product type.
ai-native userSet up automations that run autonomously in the background
weight 2 · not comparableRadeon RX 9070 XTn/aThis is a GPU hardware product; autonomous background automation is an application/software-orchestration capability, not something a graphics card ships itself. The evidence only covers driver/software stack support (ROCm, PyTorch) for running AI workloads, not automation/agent orchestration features.
ai-native userExplore an interactive API reference with runnable examples
weight 2 · not comparableRadeon RX 9070 XTn/aThe RX 9070 XT is a physical GPU product, not an API/SaaS product with a callable API reference; this axis targets developer-facing API docs and does not apply to a hardware product's own interface (ROCm software docs are a separate ecosystem artifact, not an interactive API reference for the GPU itself).
ai-native userDownload a machine-readable API spec (OpenAPI or equivalent)
weight 2 · not comparableRadeon RX 9070 XTn/aThe RX 9070 XT is a consumer GPU hardware product, not an API/service product; a machine-readable API spec is a category error for this kind of product.
NVIDIA H200 (SXM)none0/10The H200 is a hardware GPU; NVIDIA's developer portal was probed for machine-readable API specs (openapi.json, swagger.json, etc.) and all returned 404, showing no discoverable OpenAPI spec is published.
ai-native userTest against a sandbox environment without touching production data
weight 1 · not comparableRadeon RX 9070 XTn/aThis story concerns sandboxed testing environments isolated from production data, which is a software/platform concern, not applicable to a GPU hardware product like the RX 9070 XT.
ai-native userRely on versioned APIs with a documented deprecation policy
weight 2 · not comparableRadeon RX 9070 XTn/aA GPU hardware product is not itself an API service; versioned APIs with deprecation policies apply to software platforms/services, not to a graphics card as a category.
ai-native userDefine rules that trigger actions automatically on events
weight 3 · not comparableRadeon RX 9070 XTn/aThis is a GPU hardware product; defining automation rules that trigger actions on events is a software/platform automation feature, not something a graphics card itself provides—this is a category mismatch (wrong axis).
ai-native userVersion, review, and roll back my automations
weight 1 · not comparableRadeon RX 9070 XTn/aThis story concerns versioning/reviewing/rolling back automations, an application/workflow-orchestration feature; a GPU hardware product has no such capability layer to evaluate.
ai-native userDo everything through the API that I can do in the UI
weight 2 · not comparableRadeon RX 9070 XTn/aThis is a GPU hardware product, not a service with a UI/API duality; the story asks about API-vs-UI parity, which is a category error for a physical graphics card (software stacks like ROCm are separate products).
ai-native userExport all of my data in open formats and leave
weight 3 · not comparableRadeon RX 9070 XTn/aThis story concerns data export/portability, which applies to SaaS/data platforms, not a consumer GPU hardware product; a GPU does not hold user data to export.
ai-native userChoose where my data is stored (region/residency)
weight 2 · not comparableRadeon RX 9070 XTn/aThe RX 9070 XT is a consumer GPU hardware product, not a data storage/hosting service; data residency/region selection is not an applicable axis for locally-installed hardware.
NVIDIA H200 (SXM)n/aThe H200 is a hardware GPU/chip, not a hosted data storage or cloud service; data residency/region selection is a deployment-layer concern determined by whoever operates the data center, not a property of the GPU itself. This axis is a category error for a hardware product.
ai-native userControl data retention and deletion
weight 2 · not comparableRadeon RX 9070 XTn/aA GPU hardware product is not a data-processing service that retains user data; data retention/deletion controls are a SaaS/cloud-service axis, not applicable to a local GPU/driver stack.
ai-native userOpt out of telemetry and usage tracking
weight 2 · not comparableRadeon RX 9070 XTn/aThis is a hardware product (GPU); telemetry opt-out settings would belong to bundled driver software, not a fair axis for evaluating the GPU itself as an AI-native product capability.