2-GPU systems including R9700 LLM benchmarks
2,565 results · 4,164 measurements · 65 sources
Device specifications
| Variant | Memory | Memory type | Bus | Bandwidth | FP16 matrix | INT8 matrix |
|---|---|---|---|---|---|---|
| R9700 ↗ | 32 GB | GDDR6 | 256-bit | 640 GB/s | 191 TFLOPS | 383 TOPS |
Manufacturer specifications. Shared system RAM is not dedicated VRAM. Unreported values remain —; measured LLM results retain their reported configuration.
Selected reported tests
24 of 2,565 resultsSource-reported results, selected across reports by documentation quality. Match configurations before comparing values.
| View ReportCustom evaluation | Qwen3.6-27B | ScaffoldBenchV4 · Six scenarios · SB-10, 15, 20, 30, 35, 491 concurrent request | 40 / 53Score · Custom rubric | — | — | 2 × R9700Layer split · 32 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportCustom evaluation | Devstral-24B | MMLU57 subjects · first item per subject1 concurrent request | 80.7 %Accuracy · 46 / 57 · Exact-choice parser | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Laguna-XS.2 | Tool-use ladderDepth rung 1 of7; 3 profile(s) · schema-v2 / agentic-code-log-v116,453 input · 1 concurrent request | 100 %Checks passed · 3 / 3 · Tool-use checks | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B | Tool-use ladderDepth rung 1 of7; 1 profile(s) · schema-v2 / repeated-v116,784 input · 1 concurrent request | 100 %Checks passed · 1 / 1 · Tool-use checks | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportCoding session | Qwen3.8-Flash-Next | Terminal-Bench-LocalCore19 v1.0.0 · Core19 full19-task computing subset1 concurrent request | 89.47 %pass@2 · retry failures · 17 / 19 · Executable verifiers | — | — | 2 × R9700Multi-GPU · split unknownConfiguration
|
| View ReportCoding session | Qwen3.6-27BPartial evaluation | SWE-bench Verified MiniVerified Mini: 50 tasks (25 Django + 25 Sphinx) | 74 %LLM judge · 37 / 50 66 %Exit-zero rate · 33 / 50 · Container test exit | — | — | 2 × R9700Multi-GPU · split unknownConfiguration
|
| View ReportCustom evaluation | Qwen2.5-7B-Instruct | Unspecified evaluation512 configured context | 7.552 PPLScore · Lower is better | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-Flash-Next uncensored fine-tune (exact checkpoint unreported) | HumanEval164 problems | 88.4 %Reported pass@1 · n = 164 | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | gemma-4-26B-A4B-it-MXFP4-Quark-RDNA4 | tau2-bench telecom114 telecom tasks6 concurrent requests | 46.49 %Reward · 53 / 114 | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportCustom evaluation | Ornith-1.5-35B-A3B-MXFP4-Quark-RDNA4 | GSM8K50 prompts per seed; flexible extraction | 90 %Accuracy · flexible extraction · Median | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Muse-Glimmer-30B-MXFP4-Quark-RDNA4 | tau2-bench telecom114 telecom tasks6 concurrent requests | 84.21 %Reward · 96 / 114 | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27BCorrectness concern | Tool schema30 forced structured-output requests | 30 passesScore · 30 / 30 · Schema-validation passes | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportCustom evaluation | Qwen3.8-27B-NVFP4 | GSM8K500 questions8 concurrent requests | 97.6 %Accuracy · 488 / 500 · Reported correctness | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportBetterBench | Qwen3.8-27B | Token speed0.2.3 · chat | — | 1,000.5 tok/sPrefill · median · per request | 67.6 tok/sGeneration · median · per request | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Qwen3.6-27B | Token speed | — | 733.33 tok/sPrefill · per request | 17.61 tok/sGeneration · per request | 2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | DeepSeek-V4.1-Flash-1017-GSQ-RCO | Token speedISO-8601 duration parser | — | 2.07 tok/sPrefill · per request | 6.27 tok/sGeneration · per request | Mixed: AMD Radeon AI PRO R9700 (32 GB) + AMD Radeon RX 7900 XTX (24 GB) · 2 GPUsLayer splitConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27BConflicting evidence | Token speed | — | 1,458 tok/sPrefill · per request | 29.7 tok/sGeneration · per request | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportBetterBench | Qwen3.8-27B | BetterBench0.2.2 | 94.9 tok/sInter-token · p50 · per request | 1,879.4 tok/sPrefill · p50 · per request | 95.8 tok/sGeneration · p50 · per request | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B | Token speed | — | — | 70.86 tok/sGeneration · per request | Mixed: AMD Radeon AI PRO R9700 32GB + AMD Radeon RX 9070 XT 16GB · 2 GPUsLayer splitConfiguration
|
| View ReportServing benchmark | Qwen3.8-Flash-Next-R9V | Token speed | — | — | 36.03 tok/sGeneration · mean · per request | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-Flash-Next-R9V | Token speed | — | 489.53 tok/sPrefill · mean · per request | — | 2 × R9700Layer split · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Huihui-Qwen3.6-27B-abliterated | Token speed | — | 812.22 tok/sPrefill · mean · per request | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.5-27B | Token speed | — | — | 26.7 tok/sGeneration · mean · per request | 2 × R9700Row split · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.5-27B | Token speed | — | — | 26.29 tok/sGeneration · mean · per request | 2 × R9700Row split · 32 GB VRAM/GPUConfiguration
|
Models and software in this collection
Model families: DeepSeek MoE, DeepSeek R1, DeepSeek V4, DeepSeek V4.1, Devstral, Devstral 2, GLM 4.7, GPT-OSS, Gemma 3, Gemma 4, Laguna, Llama 3, Llama 3.1, Llama 3.2, Mistral, Muse Glimmer, Nemotron 3, North Mini Code, Qwen2.5, Qwen3, Qwen3.5, Qwen3.6, Qwen3.8
Engines: Affinity, LM Studio, R9V / vLLM, Radiance, Radiance standalone, SGLang, Strata, llama.cpp, llama.cpp / ROCmFPX, public vLLM Radiance comparator, vLLM, vLLM (Capicua25x RDNA4 port), vLLM + r9700-stack, vLLM / Radiance, vLLM Radiance, vLLM Radiance MXFP4, vLLM-Radiance, vLLM_for_AMD, vllm
Methodology and evidence standards · Download the research dataset