LLM EXPLORER 58,531 MODELS INDEXED

DeepSeek V4 Flash 0731 REAM144 163B by WaveCut

By WaveCut · 241 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash 0731 REAM144 163B is an open-source language model by WaveCut. Features: 163b LLM, VRAM: 102.6GB, Context: 1024K, License: mit, LLM Explorer Score: 0.31.

  8-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek-v4   Deepseek v4   En   Endpoints compatible   Es   Fp8   Mixture-of-experts   Pruning   Ream   Region:us   Ru   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/WaveCut/DeepSeek-V4-Flash-0731-REAM144-163B 

DeepSeek V4 Flash 0731 REAM144 163B Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 REAM144 163B
Repository 🤗https://huggingface.co/WaveCut/DeepSeek-V4-Flash-0731-REAM144-163B 
Base Model(s)  DeepSeek V4 Flash 0731   deepseek-ai/DeepSeek-V4-Flash-0731
Model Size163b
Required VRAM102.6 GB
Updated2026-08-15
MaintainerWaveCut
Model Typedeepseek_v4
Model Files  4.3 GB: 1-of-24   4.3 GB: 2-of-24   4.3 GB: 3-of-24   4.3 GB: 4-of-24   4.3 GB: 5-of-24   4.3 GB: 6-of-24   4.3 GB: 7-of-24   4.3 GB: 8-of-24   4.3 GB: 9-of-24   4.3 GB: 10-of-24   4.3 GB: 11-of-24   4.3 GB: 12-of-24   4.3 GB: 13-of-24   4.3 GB: 14-of-24   4.3 GB: 15-of-24   4.3 GB: 16-of-24   4.3 GB: 17-of-24   4.3 GB: 18-of-24   4.3 GB: 19-of-24   4.3 GB: 20-of-24   4.3 GB: 21-of-24   4.3 GB: 22-of-24   4.3 GB: 23-of-24   3.7 GB: 24-of-24
Supported Languagesen ru zh es
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