LLM EXPLORER 62,233 MODELS INDEXED

DeepSeek V4 Flash by ElytronAI

By ElytronAI · 321 downloads
HF Repo ↗ Copy URL

DeepSeek V4 Flash is an open-source language model by ElytronAI. Features: 165.9b LLM, VRAM: 148.5GB, Context: 1024K, License: mit, LLM Explorer Score: 0.32.

  8-bit Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Custom-layout   Deepseek v4   Image-text-to-text   Moe   Mxfp4   Mxfp8   Pulsar   Pulsar-safetensors   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/ElytronAI/DeepSeek-v4-Flash 

DeepSeek V4 Flash Parameters and Internals

LLM NameDeepSeek V4 Flash
Repository 🤗https://huggingface.co/ElytronAI/DeepSeek-v4-Flash 
Base Model(s)  DeepSeek V4 Flash Vision Exp   deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Model Size165.9b
Required VRAM148.5 GB
Updated2026-09-26
MaintainerElytronAI
Model Typedeepseek_v4
Model Files  0.9 GB: 1-of-48   3.6 GB: 2-of-48   3.6 GB: 3-of-48   3.6 GB: 4-of-48   3.6 GB: 5-of-48   3.6 GB: 6-of-48   3.6 GB: 7-of-48   3.6 GB: 8-of-48   3.6 GB: 9-of-48   3.6 GB: 10-of-48   3.6 GB: 11-of-48   3.6 GB: 12-of-48   3.6 GB: 13-of-48   3.6 GB: 14-of-48   3.6 GB: 15-of-48   3.6 GB: 16-of-48   3.6 GB: 17-of-48   3.6 GB: 18-of-48   3.6 GB: 19-of-48   3.6 GB: 20-of-48   3.6 GB: 21-of-48   3.6 GB: 22-of-48   3.6 GB: 23-of-48   3.6 GB: 24-of-48   3.6 GB: 25-of-48   3.6 GB: 26-of-48   3.6 GB: 27-of-48   3.6 GB: 28-of-48   3.6 GB: 29-of-48   3.6 GB: 30-of-48   3.6 GB: 31-of-48   3.6 GB: 32-of-48   3.6 GB: 33-of-48   3.6 GB: 34-of-48   3.6 GB: 35-of-48   3.6 GB: 36-of-48   3.6 GB: 37-of-48   3.6 GB: 38-of-48   3.6 GB: 39-of-48   3.6 GB: 40-of-48   3.6 GB: 41-of-48   3.6 GB: 42-of-48
Model ArchitectureDeepseekV4ForCausalLM
Licensemit
Context Length1048576
Model Max Length1048576
Transformers Version5.0.0
Vocabulary Size129280
Torch Data Typebfloat16