deepseek-v4.1POST
Strata 0.2.4 adds DeepSeek V4.1 Flash 1.75–2.25 bit GGUF quants
The release ships IQ1_M at 239GB, IQ2_XXS at 257GB and IQ2_XS at 274GB quantized weights, published on Hugging Face.
大卫叔的AI旅程
@aidavid125Archived 7 days agoOriginally posted 2026.10.24
大卫叔的AI旅程 @aidavid125Originally posted 2026.10.24
Strata新版本0.2.4发布： - 已经支持DeepSeek-V4.1-Flash - IQ1_M (1.75 bits) 239 GB - IQ2_XXS (2.00 bits) 257 GB - IQ2_XS (2.25 bits) 274 GB 模型链接： https://huggingface.co/ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-GGUF
This post quotes another post: “DeepSeek V4.1 Flash runs on 64GB RAM via Strata and GSQ-RCO quants”
x.com/aidavid125/status/2113842784256024744Archived 2026.10.24 12:06