LLM EXPLORER 65,418 MODELS INDEXED

DeepSeek V4.1 Flash 1017 4bit Paged by GreenBitAI

By GreenBitAI · 645 downloads
HF Repo ↗ Copy URL

DeepSeek V4.1 Flash 1017 4bit Paged is an open-source language model by GreenBitAI. Features: 8.8b LLM, VRAM: 11.3GB, License: mit, Quantized, LLM Explorer Score: 0.34.

  4-bit   4bit   Apple-silicon Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek v41   Expert-paging   Fp8   Gbx-lm   Image-text-to-text   Mixture-of-experts   Mlx   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/GreenBitAI/DeepSeek-V4.1-Flash-1017-4bit-paged 

DeepSeek V4.1 Flash 1017 4bit Paged Parameters and Internals

LLM NameDeepSeek V4.1 Flash 1017 4bit Paged
Repository 🤗https://huggingface.co/GreenBitAI/DeepSeek-V4.1-Flash-1017-4bit-paged 
Base Model(s)  deepseek-ai/DeepSeek-V4.1-Flash-1017   deepseek-ai/DeepSeek-V4.1-Flash-1017
Model Size8.8b
Required VRAM11.3 GB
Updated2026-10-22
MaintainerGreenBitAI
Model Typedeepseek_v41
Model Files  306.0 GB   11.3 GB
Quantization Type4bit
Model ArchitectureDeepseekV41ForCausalLM
Licensemit
Model Max Length1048576
Transformers Version5.6.0
Tokenizer ClassPreTrainedTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>