hanxiao/DeepSeek-V4.1-Flash-1017-FP8-abliterated-4x-RTX-PRO-6000
Abliterated DeepSeek-V4.1-Flash-1017 (FP8 dense, FP4 experts) on 4x RTX PRO 6000 with vLLM-Moet r21 and DSpark: 371-376 tok/s single-stream agent decode at 30k-120k context, 1M context, Flex-start GCE VM
GitHub repository with 31 stars and 5 forks.
Language: Shell
Topics: abliterated, blackwell, deepseek, deepseek-v4, flex-start, fp4, fp8, gcp, llm-inference, rtx-pro-6000