Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
24 selected tests| View Reportllm-bench.io | Qwen3.6-27B | llm-bench.io QualityFour sequential scenarios: agent workflow, code generation, role play, research | 79.61 / 100LLM judge · Mean | — | 10.41 tok/sGeneration · mean · per request | GPU count unknownUnknown · 24 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportGeneric LLM | Qwen3.6-27B | HumanEvalFull164problems | 78.05 %pass@1 · 128 / 164 · Executable tests 16.8 tok/sThroughput · aggregate | — | — | 1 × RX 9070Single GPU · 16 GB VRAM/GPUConfiguration
|
| 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 ReportGeneric LLM | Qwen3.6-27B | MBPPMBPP+ v0.2.0 · Base tests · 378 tasks1 concurrent request | 92.06 %Tests · pass@1 · 348 / 378 | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| 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 ReportCoding session | Qwen3.6-27BPartial evaluation | SWE-bench Verified MiniVerified Mini: 50 tasks (25 Django + 25 Sphinx) | 70 %LLM judge · 35 / 50 58 %Exit-zero rate · 29 / 50 · Container test exit | — | — | 1 × R9700Single GPUConfiguration
|
| View ReportCoding session | Qwen3.6-27BPartial evaluation | SWE-bench Verified MiniVerified Mini: 50 tasks (25 Django + 25 Sphinx) | 72 %LLM judge · 36 / 50 62 %Exit-zero rate · 31 / 50 · Container test exit | — | — | 1 × R9700Single GPUConfiguration
|
| View ReportCoding session | Qwen3.6-27B | Token speed | 17.14 tok/sThroughput · per request | 1,592.45 tok/sPrefill · per request | 23.5 tok/sGeneration · per request | 2 × RX 9070 XTLayer split · 16 GB VRAM/GPUConfiguration
|
| View ReportKyuz MTP | Qwen3.6-27B | Token speed | — | 113.88 tok/sPrefill · per request | 26.67 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Qwen3.6-27B | Token speed | — | 466.57 tok/sPrefill · median · per request | 277.97 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Qwen3.6-27B | Token speed | — | 112.1 tok/sPrefill · median · unknown | 33.8 tok/sGeneration · median · unknown | 1 × Ryzen AI Max+ 395Single GPU · Unified memoryConfiguration
|
| View ReportLocalMaxxing | Qwen3.6-27B | Token speed | — | 375 tok/sPrefill · per request | 60.6 tok/sGeneration · per request | 1 × RX 7900 XTSingle GPU · 20 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Qwen3.6-27B | Token speed | — | 334.59 tok/sPrefill · unknown | 232.14 tok/sGeneration · unknown | 1 × RX 7900 XTXSingle GPU · 24 GB VRAM/GPUConfiguration
|
| View ReportVS Code agent log | Qwen3.6-27B | Token speedMoorhuhn | — | 73.87 tok/sPrefill · per request | 38.13 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.6-27B | Token speed | — | 1,141.62 tok/sPrefill · median · per request | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.6-27BConflicting evidence | Token speed | 15.88 tok/sThroughput · per request | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.6-27B | Token speed | 17 tok/sThroughput · per request | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3.6-27B | Token speed512 input tokens · 0 existing KV tokens | — | 723.55 tok/sPrefill · mean · per request | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3.6-27B | Token speed512 input tokens · 0 output tokens · 0 existing KV tokens | — | 367.47 tok/sPrefill · mean · per request | — | 1 × Ryzen AI Max+ 395Single GPU · Unified memoryConfiguration
|
| View Reportllama-bench | Qwen3.6-27B | Token speed2,048 input tokens · 16,384 existing KV tokens | — | 680.35 tok/sPrefill · mean · per request | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3.6-27B | Token speed | — | 525.9 tok/sPrefill · per request | — | 1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportLocalMaxxing | Qwen3.6-27B | Token speed | — | — | 24.91 tok/sGeneration · unknown | 1 × RX 9070 XTSingle GPU · 16 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.6-27B | Token speed | 99.23 tok/sThroughput · aggregate | — | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3.6-27B | Token speed | — | 956.41 tok/sPrefill · mean · per request | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: BF16, FP8, INT4 AutoRound, INT4 W4A16, IQ3_XXS, IQ4_XS, llmfan46 Q5_K_M, MQ4, MQ4-AWQ, Q4_0, Q4_K_M, Q4_K_S, Q4_K_XL, Q5 (Unsloth), Q5_K, Q5_K_M, Q8_0, Q8_0_ROCMFPX, Q8_K_XL, Quark-W8A8-INT8, TQ3_4S, UD-IQ3_XXS, UD-Q4_K_XL, UD-Q4_K_XL + Q8_0 mmproj, UD-Q5_K_XL, UD-Q6_K_XL, UD-Q8_K_XL
Engines: hipfire, LLAMA-DX / llama.cpp fork, llama.cpp, llama.cpp / ROCmFPX, llama.cpp RDNA lab fork, llama.cpp TurboQuant fork, LM Studio, ollama, vllm, vLLM, vLLM Radiance
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700 · RX 9070 XT · RX 9070 · RX 7900 XTX · RX 7900 XT · Ryzen AI Max+ 395