Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
24 selected tests| View ReportCustom evaluation | Qwen3.8-Flash-Next | AIME24LLST protocol 1.0 subset · 10 pinned LLST v1.0 questions; not the full AIME24 benchmark32K configured context | 30 %Score · n = 100 · Strict numeric extraction | — | — | 2 × RX 7900 XTXMulti-GPU · split unknown · 24 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 | Qwen3.8-Flash-Next | Neon LadderContract v2_12 · Neon Overdrive game-generation contract v2_121 concurrent request | 16 checksScore · 16 / 19 · 19 static checks; not a human playtest grade | — | — | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAMConfiguration
|
| View ReportLocalMaxxing | Qwen3.8-Flash-Next | Token speed | — | 678 tok/sPrefill · unknown | 41.4 tok/sGeneration · unknown | 1 × Ryzen AI Max+ 395Single GPU · Unified memoryConfiguration
|
| View ReportLocalMaxxing | Qwen3.8-Flash-Next | Token speed | — | 474.37 tok/sPrefill · unknown | 28.13 tok/sGeneration · peak · unknown | 3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportCoding session | Qwen3.8-Flash-Next | Token speedsix-turn synthetic coding-agent conversation | — | 248.83 tok/sPrefill · per request | 20.29 tok/sGeneration · per request | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAMConfiguration
|
| View ReportServing benchmark | Qwen3.8-Flash-Next | Token speed | — | 564.14 tok/sPrefill · per request | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3.8-Flash-Next | Token speed512 input tokens · 0 existing KV tokens | — | 1,138 tok/sPrefill · per request | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportBetterBench | Qwen3.8-Flash-Next | BetterBench | — | 3,207.8 tok/sPrefill · median · per request | — | 4 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportBetterBench | Qwen3.8-Flash-Next | BetterBench0.2.2 · Corpus 1.0 · 8k context preset | — | 1,727 tok/sPrefill · median · per request | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-Flash-Next | Token speed | 36.3 tok/sThroughput · per request | — | — | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAMConfiguration
|
| View ReportServing benchmark | Qwen3.8-Flash-Next | Token speed | — | — | 219 tok/sGeneration · per request | 4 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-Flash-Next | Token speed | — | — | 82.5 tok/sGeneration · per request | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportCustom evaluation | Qwen3.8-Flash-Next | IFEvalLLST protocol 1.0 subset · 20 pinned LLST v1.0 questions; not the full IFEval benchmark32K configured context | 95 %Score · n = 100 · Source aggregate; exact strict/loose and prompt/instruction submetric unspecified | — | — | 2 × RX 7900 XTXMulti-GPU · split unknown · 24 GB VRAM/GPUConfiguration
|
| View ReportCoding session | Qwen3.8-Flash-Next | Terminal-Bench-LocalCore19 v1.0.0 · break-filter-js-from-html1 concurrent request | Passed pass@2 · retry failures · 1 / 1 · Executable verifiers | — | — | 2 × R9700Multi-GPU · split unknownConfiguration
|
| View ReportCoding session | Qwen3.8-Flash-Next | Neon LadderContract v2_12 · Neon Overdrive game-generation contract v2_121 concurrent request | 17 checksScore · 17 / 19 · 19 static checks; not a human playtest grade | — | — | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAMConfiguration
|
| View ReportLocalMaxxing | Qwen3.8-Flash-Next | Token speed | — | 920 tok/sPrefill · unknown | 33.5 tok/sGeneration · unknown | 1 × Ryzen AI Max+ 395Single GPU · Unified memoryConfiguration
|
| View ReportLocalMaxxing | Qwen3.8-Flash-Next | Token speed | — | 572.4 tok/sPrefill · unknown | 31.11 tok/sGeneration · peak · unknown | 3 × R9700Multi-GPU · split unknown · 32 GB VRAM/GPUConfiguration
|
| View ReportCoding session | Qwen3.8-Flash-Next | Token speedsix-turn synthetic coding-agent conversation | — | 193 tok/sPrefill · per request | 20.42 tok/sGeneration · per request | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAMConfiguration
|
| View ReportServing benchmark | Qwen3.8-Flash-Next | Token speed | — | 564.35 tok/sPrefill · per request | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View Reportllama-bench | Qwen3.8-Flash-Next | Token speed512 input tokens · 4,096 existing KV tokens | — | 1,086 tok/sPrefill · per request | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportBetterBench | Qwen3.8-Flash-Next | BetterBench | — | 3,508.6 tok/sPrefill · median · per request | — | 4 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportBetterBench | Qwen3.8-Flash-Next | BetterBench0.2.2 · Corpus 1.0 · 8k context preset | — | 1,986 tok/sPrefill · median · per request | — | 2 × R9700Tensor parallel · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-Flash-Next | Token speed | 47.6 tok/sThroughput · per request | — | — | 1 × Ryzen AI Max+ 395Single GPU · Unified memory · 128 GB RAMConfiguration
|
Quantizations and software
Quantizations: FP8+IQ4R_MOE, HGN v2 (custom), IQ4_XS, MXFP4, MXFP4 experts / FP8 dense, Q4_0_ROCMFP4_FAST, Q4_0_ROCMI4, UD-IQ3_XXS, UD-IQ4_XS, UD-IQ4_XS + Q6_K, UD-Q2_K_XL, UD-Q3_K_XL, UD-Q4_K_XL, W4B
Engines: custom, Gufo, Halogen, llama.cpp, llama.cpp (halo-box-strix), llama.cpp (Nathan Vulkan fork), Loculus Core, R9V / vLLM, ranma.cpp, Strata, vLLM, vLLM + r9700-stack
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700 · RX 7900 XTX · Ryzen AI Max+ 395