LLM EXPLORER 57,918 MODELS INDEXED

DeepSeek V4 Flash 0731 2.4bit Mixed by mlx-community

By mlx-community · 1499 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash 0731 2.4bit Mixed is an open-source language model by mlx-community. Features: 25.7b LLM, VRAM: 92.4GB, Context: 1024K, License: mit, LLM Explorer Score: 0.36.

  2-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek   Deepseek v4   Mlx   Moe   Oq   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed 

DeepSeek V4 Flash 0731 2.4bit Mixed Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 2.4bit Mixed
Repository 🤗https://huggingface.co/mlx-community/DeepSeek-V4-Flash-0731-2.4bit-mixed 
Base Model(s)  DeepSeek V4 Flash 0731   deepseek-ai/DeepSeek-V4-Flash-0731
Model Size25.7b
Required VRAM92.4 GB
Updated2026-08-10
Maintainermlx-community
Model Typedeepseek_v4
Model Files  4.0 GB: 1-of-18   4.9 GB: 2-of-18   5.4 GB: 3-of-18   5.4 GB: 4-of-18   5.4 GB: 5-of-18   5.4 GB: 6-of-18   5.4 GB: 7-of-18   5.4 GB: 8-of-18   5.4 GB: 9-of-18   5.4 GB: 10-of-18   5.4 GB: 11-of-18   5.4 GB: 12-of-18   5.4 GB: 13-of-18   5.4 GB: 14-of-18   5.4 GB: 15-of-18   5.4 GB: 16-of-18   4.4 GB: 17-of-18   3.5 GB: 18-of-18
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version4.57.1
Tokenizer ClassPreTrainedTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size129280
Torch Data Typebfloat16