deepseek-v4.1IMAGE
DeepSeek V4.1 Flash on one RTX 5090: custom GGUF quant hits 21 tok/s
The author releases an IQ2_XXS GGUF quant and recipe, reporting ~21 tok/s on fresh prompts and 25 on repeats on a single RTX 5090, versus ~7 with MXFP4 experts.
Adrian Rangel
@acrogenesisArchived 12 days agoOriginally posted 2026.10.18
Adrian Rangel @acrogenesisOriginally posted 2026.10.18
New Deepseek Flash V4.1 1017. One RTX 5090. ~21 tokens/sec. My custom GGUF quant hits 21 tok/s on fresh prompts and 25 on repeats, versus ~7 with MXFP4 experts. Weights, recipe, benchmarks: https://huggingface.co/acrogenesis/DeepSeek-V4.1-Flash-1017-IQ2_XXS-GGUF
x.com/acrogenesis/status/2111643296405836145Archived 2026.10.18 16:44