8 threads
3 records across 1 models (quants: IQ1_M main / Q8_0 head).
| hardware | model | quant | backend | tok/s | pp tok/s | W | ttft s | ctx/tg | date | class | flags | source |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 8 threads | Qwen3.8-Flash-Next | IQ1_M main / Q8_0 head | llama.cpp (CPU) | 5.61 | – | – | – | 4096 | 2026-10-02 | community | – | source |
| 8 threads | Qwen3.8-Flash-Next | IQ1_M main / Q8_0 head | llama.cpp (CPU) | 5.13 | – | – | – | 4096 | 2026-10-02 | community | – | source |
| 8 threads | Qwen3.8-Flash-Next | IQ1_M main / Q8_0 head | llama.cpp (CPU) | 3.49 | – | – | – | 4096 | 2026-10-02 | community | – | source |
All rows cite their source. Provenance: community 40018 sourced 1085