LLM EXPLORER 61,405 MODELS INDEXED

DeepSeek V4 Flash MTP Bf16 by mlx-community

By mlx-community · 1217 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash MTP Bf16 is an open-source language model by mlx-community. Features: 1.1b LLM, VRAM: 3.6GB, License: mit, LLM Explorer Score: 0.27.

  8-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Bf16   Deepseek-v4   Deepseek-v4-flash   Deepseek v4 mtp   Draft-model   En   Mlx   Mlx-vlm   Mtp   Region:us   Safetensors   Speculative-decoding
Model Card on HF 🤗: https://huggingface.co/mlx-community/DeepSeek-V4-Flash-MTP-bf16 

DeepSeek V4 Flash MTP Bf16 Parameters and Internals

LLM NameDeepSeek V4 Flash MTP Bf16
Repository 🤗https://huggingface.co/mlx-community/DeepSeek-V4-Flash-MTP-bf16 
Base Model(s)  DeepSeek V4 Flash   deepseek-ai/DeepSeek-V4-Flash
Model Size1.1b
Required VRAM3.6 GB
Updated2026-08-10
Maintainermlx-community
Model Typedeepseek_v4_mtp
Model Files  3.6 GB
Supported Languagesen
Licensemit
Model Max Length1048576
Tokenizer ClassPreTrainedTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>