LLM EXPLORER 66,704 MODELS INDEXED

DeepSeek V4.1 Flash 1017 GSQ RCO Coder MLX by mbrown-uno

By mbrown-uno · 527 downloads
HF Repo ↗ Copy URL

DeepSeek V4.1 Flash 1017 GSQ RCO Coder MLX is an open-source language model by mbrown-uno. Features: 69.2b LLM, VRAM: 226.6GB, License: mit, Code Generating.

  Arxiv:2604.18556   Arxiv:2605.00649   Agentic   Apple-silicon Base model:ista-daslab/deepsee... Base model:quantized:ista-dasl...   Code   Codegen   Conversational   Deepseek v41   Dspark   En   Expert-pruning   Image-text-to-text   Mlx   Moe   Mtp   Omlx   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Tool-calling
Model Card on HF 🤗: https://huggingface.co/mbrown-uno/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-MLX 

DeepSeek V4.1 Flash 1017 GSQ RCO Coder MLX Parameters and Internals

LLM NameDeepSeek V4.1 Flash 1017 GSQ RCO Coder MLX
Repository 🤗https://huggingface.co/mbrown-uno/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-MLX 
Base Model(s)  ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF   deepseek-ai/DeepSeek-V4.1-Flash-1017   ISTA-DASLab/DeepSeek-V4.1-Flash-1017-GSQ-RCO-Coder-GGUF   deepseek-ai/DeepSeek-V4.1-Flash-1017
Model Size69.2b
Required VRAM226.6 GB
Updated2026-11-05
Maintainermbrown-uno
Model Typedeepseek_v41
Model Files  5.9 GB: 1-of-21   6.0 GB: 2-of-21   5.5 GB: 3-of-21   6.0 GB: 4-of-21   5.5 GB: 5-of-21   6.0 GB: 6-of-21   5.6 GB: 7-of-21   6.0 GB: 8-of-21   5.5 GB: 9-of-21   6.0 GB: 10-of-21   5.5 GB: 11-of-21   6.0 GB: 12-of-21   5.5 GB: 13-of-21   6.0 GB: 14-of-21   5.5 GB: 15-of-21   6.0 GB: 16-of-21   2.3 GB: 17-of-21   61.4 GB: 18-of-21   61.4 GB: 19-of-21   5.4 GB: 20-of-21   3.6 GB: 21-of-21
Supported Languagesen
Generates CodeYes
Model ArchitectureDeepseekV41ForCausalLM
Licensemit
Model Max Length1048576
Transformers Version5.6.0
Tokenizer ClassPreTrainedTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>