LLM EXPLORER 62,696 MODELS INDEXED

DeepSeek V4 Flash 0731 RAZOR 156B A13B E128of256 by Nickyang

By Nickyang · 202 downloads

DeepSeek V4 Flash 0731 RAZOR 156B A13B E128of256 is an open-source language model by Nickyang. Features: 156b LLM, VRAM: 8GB, Context: 1024K, License: mit, LLM Explorer Score: 0.31.

  Arxiv:2609.30465   8-bit Base model:deepseek-ai/deepsee... Base model:finetune:deepseek-a...   Deepseek   Deepseek v4   Endpoints compatible   Expert-pruning   Fp4   Fp8   Mixture-of-experts   Moe   Pruning   Razor   Region:us   Safetensors

DeepSeek V4 Flash 0731 RAZOR 156B A13B E128of256 Parameters and Internals

LLM NameDeepSeek V4 Flash 0731 RAZOR 156B A13B E128of256
Repository 🤗https://huggingface.co/Nickyang/DeepSeek-V4-Flash-0731-RAZOR-156B-A13B-E128of256 
Base Model(s)  DeepSeek V4 Flash 0731   deepseek-ai/DeepSeek-V4-Flash-0731
Model Size156b
Required VRAM8 GB
Updated2026-10-01
MaintainerNickyang
Model Typedeepseek_v4
Model Files  8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.0 GB   8.1 GB   0.0 GB
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