2026-10-24 · America/Los_Angeles · 社区动态 · #11

[Release] ISTA GSQ-RCO GGUFs for DeepSeek-V4.1-Flash-1017

We have released DeepSeek-V4.1-Flash-1017 quantized with GSQ and RCO, at 1.75 to 2.25 bits per weight. DeepSeek-V4.1-Flash-1017 is a sparse mixture-of-experts model: 384 routed experts per layer, of which 6 are active per token, 763.2B parameters and a 1M-token context window. It is released with FP8 dense weights and FP4 routed experts. What's inside Three quantized GGUFs: IQ1_M (1.75 bpw), IQ2_XXS (2.00 bpw) and IQ2_XS (2.25 bpw), with backbones of 120.7 to 155.2 GB. The bit-width is the average over the 551.9B backbone parameters, which is what the search controls. One shared Engram file…

热度 45.9 / 100；排名与评分保留该期记录。