Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP on R9700
102 results · 2 sources · 230 measurements
Grouped by reported model identity. Exact weights, quantizations and software can differ. How results are reviewed
Documented results
24 selected tests| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 840.3 tok/sPrefill · per request | 47.35 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
|---|---|---|---|---|---|---|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | — | 27.3 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 979.39 tok/sPrefill · per request | 32.48 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | — | 27.1 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 883.46 tok/sPrefill · per request | 30.18 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | — | 26.5 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 615.88 tok/sPrefill · per request | 25.72 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | — | 26.2 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 977.71 tok/sPrefill · per request | 32.19 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | — | 25.86 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 994.14 tok/sPrefill · per request | 31.38 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | — | 24.97 tok/sGeneration · median · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 882.3 tok/sPrefill · per request | 29.95 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Latency128 input · 1 output · 1 concurrent request | 271 msLatency · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 616.13 tok/sPrefill · per request | 25.73 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Latency128 input · 1 output · 1 concurrent request | 273 msLatency · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 519.19 tok/sPrefill · per request | 23.49 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Latency128 input · 1 output · 1 concurrent request | 271 msTime to first token · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 854.21 tok/sPrefill · per request | 47.57 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Latency128 input · 1 output · 1 concurrent request | 273 msTime to first token · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 1,002.24 tok/sPrefill · per request | 31.91 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Latency128 input · 128 output · 1 concurrent request | 4,925 msLatency · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportGeneric LLM | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Token speed | — | 897.95 tok/sPrefill · per request | 29.74 tok/sGeneration · per request | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
| View ReportServing benchmark | Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NEO-CODER-MAX-MTP | Latency128 input · 128 output · 1 concurrent request | 4,929 msLatency · Per request | — | — | 1 × R9700Single GPU · 32 GB VRAM/GPUConfiguration
|
Quantizations and software
Quantizations: IQ4_XS, Q4_K_M, Q4_K_S
Engines: llama.cpp, Paiton + vLLM
This is a selection across sources, not a ranking or a matched experiment. Reading benchmark reports
GPU benchmark pages: R9700