LLM EXPLORER 58,133 MODELS INDEXED

DeepSeek V4 Flash 0731 W4A16 by baicai1145

By baicai1145 · 537 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash 0731 W4A16 is an open-source language model by baicai1145. Features: 44.9b LLM, VRAM: 178.4GB, Context: 1024K, License: other, LLM Explorer Score: 0.32.

Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Compressed-tensors   Deepseek   Deepseek-v4   Deepseek v4   En   Int4   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm   W4a16   Zh
Model Card on HF 🤗: https://huggingface.co/baicai1145/DeepSeek-V4-Flash-0731-W4A16 

DeepSeek V4 Flash 0731 W4A16 Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 W4A16
Repository 🤗https://huggingface.co/baicai1145/DeepSeek-V4-Flash-0731-W4A16 
Base Model(s)  DeepSeek V4 Flash 0731   deepseek-ai/DeepSeek-V4-Flash-0731
Model Size44.9b
Required VRAM178.4 GB
Updated2026-08-11
Maintainerbaicai1145
Model Typedeepseek_v4
Model Files  5.4 GB: 1-of-34   5.4 GB: 2-of-34   5.4 GB: 3-of-34   5.4 GB: 4-of-34   5.4 GB: 5-of-34   5.4 GB: 6-of-34   5.4 GB: 7-of-34   5.4 GB: 8-of-34   5.4 GB: 9-of-34   5.4 GB: 10-of-34   5.4 GB: 11-of-34   5.4 GB: 12-of-34   5.4 GB: 13-of-34   5.4 GB: 14-of-34   5.4 GB: 15-of-34   5.4 GB: 16-of-34   5.4 GB: 17-of-34   5.4 GB: 18-of-34   5.4 GB: 19-of-34   5.4 GB: 20-of-34   5.4 GB: 21-of-34   5.4 GB: 22-of-34   5.4 GB: 23-of-34   5.4 GB: 24-of-34   5.4 GB: 25-of-34   5.4 GB: 26-of-34   5.4 GB: 27-of-34   5.4 GB: 28-of-34   5.4 GB: 29-of-34   5.4 GB: 30-of-34   5.4 GB: 31-of-34   5.3 GB: 32-of-34   4.4 GB: 33-of-34   1.3 GB: 34-of-34
Supported Languagesen zh
Model ArchitectureDeepseekV4ForCausalLM
Licenseother
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