LLM EXPLORER 58,425 MODELS INDEXED

DeepSeek V4 Flash 0731 REAM96 111B by WaveCut

By WaveCut · 35 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash 0731 REAM96 111B is an open-source language model by WaveCut. Features: 111b LLM, VRAM: 75GB, Context: 1024K, License: mit, LLM Explorer Score: 0.28.

  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-REAM96-111B 

DeepSeek V4 Flash 0731 REAM96 111B Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 REAM96 111B
Repository 🤗https://huggingface.co/WaveCut/DeepSeek-V4-Flash-0731-REAM96-111B 
Base Model(s)  DeepSeek V4 Flash 0731   deepseek-ai/DeepSeek-V4-Flash-0731
Model Size111b
Required VRAM75 GB
Updated2026-08-14
MaintainerWaveCut
Model Typedeepseek_v4
Model Files  4.3 GB: 1-of-18   4.3 GB: 2-of-18   4.3 GB: 3-of-18   4.3 GB: 4-of-18   4.3 GB: 5-of-18   4.3 GB: 6-of-18   4.3 GB: 7-of-18   4.3 GB: 8-of-18   4.3 GB: 9-of-18   4.3 GB: 10-of-18   4.3 GB: 11-of-18   4.3 GB: 12-of-18   4.3 GB: 13-of-18   4.3 GB: 14-of-18   4.3 GB: 15-of-18   4.3 GB: 16-of-18   4.3 GB: 17-of-18   1.9 GB: 18-of-18
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