flkaylor19V2EX member #846540, joined on 2026-09-07 11:59:49 +08:00Today's activity rank 19168 |
| 笔记本 125B 模型 Q4 量化, xHigh256k 调优峰值 64tps。附部署和调优源码 Local LLM • flkaylor19 • 2 days ago |
6h 9m ago Replied to a topic by sentinelK › Local LLM › 你好 NVFP4: strata-0.1.44.1, qwen3.8-flash-next, rtx pro 5000 48GB + 64GB RAM, decode 130t/s, prefill2600 t/s |