DeepSeek V4.1 Flash 1017 GSQ RCO GGUF
DeepSeek-V4.1-Flash-1017 is a sparse mixture-of-experts model with 763.2B parameters: 384 routed experts per layer, of which 6 are active per token, and a 1M-token context window.
DeepSeek V4.1 Flash 1017 GSQ RCO GGUF launched on 23 October 2026. It ranked #12 on Daily Launch on 30 October 2026 with a Launch Score of 69, from trending score 427 on Hugging Face. It moved up 10 places from the day before.
What is DeepSeek V4.1 Flash 1017 GSQ RCO GGUF?
Non-uniform GGUF quantizations of a 763B-parameter, 384-expert MoE, produced with GSQ and RCO. This repository provides GGUF quantizations of DeepSeek-V4.1-Flash-1017 at three sizes: IQ1M (1.75 bits per weight), IQ2XXS (2.00) and IQ2XS (2.25). In contrast to uniform quantization, which applies a single quantization type to all weight tensors, each model here assigns a separate quantization type to every tensor. The assignment is obtained by a gradient-based search that allocates precision according to per-tensor sensitivity, subject to a total size budget. The resulting files are standard GGUF.
From its model card on Hugging Face
DeepSeek V4.1 Flash 1017 GSQ RCO GGUF is a model by ISTA-DASLab on Hugging Face. It is released under the MIT license.
How to get DeepSeek V4.1 Flash 1017 GSQ RCO GGUF
Get it from its model card on Hugging Face.