LLM EXPLORER 57,252 MODELS INDEXED

DeepSeek V4 Flash 0731 REAP37 Native MLX by True2456

By True2456 · 2286 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash 0731 REAP37 Native MLX is an open-source language model by True2456. Features: 30.6b LLM, VRAM: 102.6GB, Context: 1024K, License: mit, LLM Explorer Score: 0.35.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek   Deepseek-v4   Deepseek v4   Fp8   Mlx   Moe   Pruning   Reap   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/True2456/DeepSeek-V4-Flash-0731-REAP37-native-MLX 

DeepSeek V4 Flash 0731 REAP37 Native MLX Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 REAP37 Native MLX
Repository 🤗https://huggingface.co/True2456/DeepSeek-V4-Flash-0731-REAP37-native-MLX 
Base Model(s)  DeepSeek V4 Flash 0731   deepseek-ai/DeepSeek-V4-Flash-0731
Model Size30.6b
Required VRAM102.6 GB
Updated2026-08-09
MaintainerTrue2456
Model Typedeepseek_v4
Model Files  4.5 GB: 1-of-25   4.3 GB: 2-of-25   4.0 GB: 3-of-25   4.4 GB: 4-of-25   4.4 GB: 5-of-25   3.8 GB: 6-of-25   3.8 GB: 7-of-25   4.5 GB: 8-of-25   4.0 GB: 9-of-25   4.0 GB: 10-of-25   3.9 GB: 11-of-25   4.1 GB: 12-of-25   4.4 GB: 13-of-25   4.1 GB: 14-of-25   4.5 GB: 15-of-25   4.3 GB: 16-of-25   4.4 GB: 17-of-25   3.9 GB: 18-of-25   4.5 GB: 19-of-25   4.2 GB: 20-of-25   4.1 GB: 21-of-25   3.9 GB: 22-of-25   4.0 GB: 23-of-25   4.1 GB: 24-of-25   2.5 GB: 25-of-25
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