DeepSeek V4 Flash 0731 MXFP4 MLX is an open-source language model by TensorFold. Features: 304.2b LLM, VRAM: 2GB, Context: 1024K, License: mit, LLM Explorer Score: 0.28.
| LLM Name | DeepSeek V4 Flash 0731 MXFP4 MLX |
| Repository 🤗 | https://huggingface.co/TensorFold/DeepSeek-V4-Flash-0731-MXFP4-MLX |
| Base Model(s) | |
| Model Size | 304.2b |
| Required VRAM | 2 GB |
| Updated | 2026-11-21 |
| Maintainer | TensorFold |
| Model Type | deepseek_v4 |
| Model Files | |
| Model Architecture | DeepseekV4ForCausalLM |
| License | mit |
| Context Length | 1048576 |
| Model Max Length | 1048576 |
| Transformers Version | 4.57.1 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Beginning of Sentence Token | <|begin▁of▁sentence|> |
| End of Sentence Token | <|end▁of▁sentence|> |
| Vocabulary Size | 129280 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| DeepSeek V4 Flash 0731 | 1024K / 152.3 GB | 785771 | 2803 |
| ...Seek V4 Flash 0731 Abliterated | 1024K / 148.7 GB | 126462 | 11 |
| ... V4 Flash 0731 Abliterated FP8 | 1024K / 145.1 GB | 5149 | 35 |
| DeepSeek V4 Flash 0731 NVFP4 | 1024K / 149.3 GB | 7421 | 6 |
| ...4 Flash 0731 Abliterated NVFP4 | 1024K / 145.5 GB | 952 | 11 |
| DeepSeek V4 Flash 0731 | 1024K / 152.3 GB | 253 | 1 |
| DeepSeek V4 Flash 0731 NVFP4 | 1024K / 156.9 GB | 307 | 23 |
| ... 0731 MXFP4 Mixed CT AutoRound | 1024K / 152.3 GB | 154 | 1 |
| ...eepSeek V4 Flash 0731 Ornstein | 1024K / 568.7 GB | 183 | 1 |
| ...Seek V4 Flash 0731 CRACK NVFP4 | 1024K / 141.5 GB | 242 | 7 |