gpt-oss-120b on AMD GPUs

187 results · 9 sources · 253 measurements

Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed

Documented results

24 selected tests


View ReportCustom evaluation	gpt-oss-120bQ4_K_MModel ref. ↗Conflicting evidence	HumanEval100 problems	94 %Reported pass@1 · n = 100	—	74.78 tok/sGeneration · mean · per request	2 × W7800Layer split · 48 GB VRAM/GPU Configuration Memory 48 GB VRAM/GPU OS Ubuntu 24.04 LTS Engine Ollama Backend ROCm Harness BoJl unified evaluation harness (2026-08) Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View ReportLocalMaxxing	gpt-oss-120bF16Model ref. ↗	Token speed	—	342.75 tok/sPrefill · median · unknown	38.83 tok/sGeneration · median · unknown	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Not reported Engine llama.cpp Backend vulkan Harness LocalMaxxing community speed test; exact client where reported Prompt / output 589 / 256 tokens Context 845 Concurrency Not reported Date 2026-07-11 Full record →
View ReportLocalMaxxing	gpt-oss-120bF16Model ref. ↗	Token speed	—	853.67 tok/sPrefill · unknown	67.16 tok/sGeneration · peak · unknown	3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend vulkan Harness LocalMaxxing community speed test; exact client where reported Prompt / output 589 / 256 tokens Context 845 Concurrency Not reported Date 2026-06-27 Full record →
View ReportGeneric LLM	gpt-oss-120bBF16Model ref. ↗Conflicting evidence	Token speed	0.2 tok/sThroughput · per request	—	—	4 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (distribution not reported) Engine vLLM Backend ROCm 7.2.2 container / 6.4.3 host Harness Not reported Prompt / output ? / ? tokens Context Not reported Concurrency 1 Date 2026-05-22 Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed512 input tokens · 0 output tokens · 0 existing KV tokens	—	625.58 tok/sPrefill · mean · per request	—	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 512 / 0 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed512 input tokens · 0 existing KV tokens	—	1,498.15 tok/sPrefill · mean · per request	—	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend vulkan_amdvlk Harness llama-bench Prompt / output 512 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed512 input tokens · 0 existing KV tokens	—	1,602.42 tok/sPrefill · mean · per request	—	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend vulkan_amdvlk Harness llama-bench Prompt / output 512 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	gpt-oss-120bMXFP4Model ref. ↗	Token speed512 input tokens · 0 existing KV tokens	—	279.07 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend ROCm Harness Not reported Prompt / output 512 / ? tokens Context Not reported Concurrency 1 Date Not reported Full record →
View ReportGeneric LLM	gpt-oss-120bQuant not reportedModel ref. ↗	Token speed	—	—	115 tok/sGeneration · per request	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Windows Engine Not reported Backend Vulkan Harness Not reported Prompt / output ? / ? tokens Context Not reported Concurrency Not reported Date 2025-10-28 Full record →
View ReportCustom evaluation	gpt-oss-120bQ4_K_MModel ref. ↗Conflicting evidence	Token speedsynth-bulk-dispatcher-impl	—	—	74.29 tok/sGeneration · mean · per request	2 × W7800Layer split · 48 GB VRAM/GPU Configuration Memory 48 GB VRAM/GPU OS Ubuntu 24.04 LTS Engine Ollama Backend ROCm Harness BoJl unified evaluation harness (2026-08) Prompt / output ? / 1674 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View ReportLocalMaxxing	gpt-oss-120bF16Model ref. ↗	Token speed	—	842.49 tok/sPrefill · unknown	72.56 tok/sGeneration · peak · unknown	3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend vulkan Harness LocalMaxxing community speed test; exact client where reported Prompt / output 589 / 256 tokens Context 845 Concurrency Not reported Date 2026-08-04 Full record →
View ReportGeneric LLM	gpt-oss-120bBF16Model ref. ↗Conflicting evidence	Token speed	—	—	5.9 tok/sGeneration · per request	4 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (distribution not reported) Engine vLLM Backend ROCm 7.2.2 container / 6.4.3 host Harness Not reported Prompt / output ? / ? tokens Context Not reported Concurrency 1 Date 2026-05-22 Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed0 input tokens · 128 output tokens · 0 existing KV tokens	—	—	51.81 tok/sGeneration · mean · per request	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 0 / 128 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed128 output tokens · 0 existing KV tokens	—	—	95.14 tok/sGeneration · mean · per request	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend vulkan_amdvlk Harness llama-bench Prompt / output ? / 128 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed128 output tokens · 0 existing KV tokens	—	—	97.96 tok/sGeneration · mean · per request	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend vulkan_amdvlk Harness llama-bench Prompt / output ? / 128 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	gpt-oss-120bMXFP4Model ref. ↗	Token speed128 output tokens · 0 existing KV tokens	—	—	26.79 tok/sGeneration · mean · per request	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend ROCm Harness Not reported Prompt / output ? / 128 tokens Context Not reported Concurrency 1 Date Not reported Full record →
View ReportCustom evaluation	gpt-oss-120bQ4_K_MModel ref. ↗Conflicting evidence	Token speedsynth-horner-mpmath-derivative	—	—	74.59 tok/sGeneration · mean · per request	2 × W7800Layer split · 48 GB VRAM/GPU Configuration Memory 48 GB VRAM/GPU OS Ubuntu 24.04 LTS Engine Ollama Backend ROCm Harness BoJl unified evaluation harness (2026-08) Prompt / output ? / 966 tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View ReportLocalMaxxing	gpt-oss-120bF16Model ref. ↗	Token speed	—	850.25 tok/sPrefill · unknown	72.81 tok/sGeneration · peak · unknown	3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend vulkan Harness LocalMaxxing community speed test; exact client where reported Prompt / output 589 / 256 tokens Context 845 Concurrency Not reported Date 2026-08-04 Full record →
View ReportGeneric LLM	gpt-oss-120bBF16Model ref. ↗Conflicting evidence	Latency1 concurrent request	19,700 msTime to first token · Per request	—	—	4 × R9700Tensor parallel · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (distribution not reported) Engine vLLM Backend ROCm 7.2.2 container / 6.4.3 host Harness Not reported Prompt / output ? / ? tokens Context Not reported Concurrency 1 Date 2026-05-22 Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed2,048 input tokens · 0 output tokens · 32,768 existing KV tokens	—	589.25 tok/sPrefill · mean · per request	—	1 × Ryzen AI Max+ 395Single GPU · Unified memory Configuration Memory Unified memory OS Fedora Linux 43 (Workstation Edition) Engine llama.cpp Backend ROCm / rocm-7_2_3 Harness llama-bench Prompt / output 2048 / 0 tokens Context Not reported Concurrency 1 Date 2026-05-16 Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed2,048 input tokens · 16,384 existing KV tokens	—	880.37 tok/sPrefill · mean · per request	—	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Linux (inferred; distribution unreported) (inferred) Engine llama.cpp Backend vulkan_amdvlk Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View Reportllama-bench	gpt-oss-120bMXFP4Model ref. ↗	Token speed2,048 input tokens · 16,384 existing KV tokens	—	1,689.14 tok/sPrefill · mean · per request	—	2 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Fedora 42 — Linux 6.15.9-201.fc42.x86_64 (Sat Aug 2 11:37:34 UTC 2025) Engine llama.cpp Backend vulkan_amdvlk Harness llama-bench Prompt / output 2048 / ? tokens Context Not reported Concurrency Not reported Date Not reported Full record →
View ReportGeneric LLM	gpt-oss-120bMXFP4Model ref. ↗	Token speed512 input tokens · 4,000 existing KV tokens	—	498.33 tok/sPrefill · mean · per request	—	1 × R9700Single GPU · 32 GB VRAM/GPU Configuration Memory 32 GB VRAM/GPU OS Arch Linux Engine llama.cpp Backend ROCm Harness Not reported Prompt / output 512 / ? tokens Context Not reported Concurrency 1 Date Not reported Full record →
View ReportCustom evaluation	gpt-oss-120bQ4_K_MModel ref. ↗Conflicting evidence	Token speedsynth-invoke-sign-artifacts-ps	—	—	74.06 tok/sGeneration · mean · per request	2 × W7800Layer split · 48 GB VRAM/GPU Configuration Memory 48 GB VRAM/GPU OS Ubuntu 24.04 LTS Engine Ollama Backend ROCm Harness BoJl unified evaluation harness (2026-08) Prompt / output ? / 1931 tokens Context Not reported Concurrency Not reported Date Not reported Full record →

Quantizations and software

Quantizations: BF16, F16, MXFP4, Q4_K_M
Engines: llama.cpp, Ollama, vllm, vLLM

Explore all 187 results →

This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports

GPU benchmark pages: W7800 · R9700 · Ryzen AI Max+ 395