LLM EXPLORER 60,958 MODELS INDEXED

DeepSeek V4.1 Flash MTPLX Streaming Q2 by OpensourceWTF

By OpensourceWTF · 932 downloads
HF Repo ↗ Copy URL

DeepSeek V4.1 Flash MTPLX Streaming Q2 is an open-source language model by OpensourceWTF. Features: 22.7b LLM, VRAM: 0.2GB, License: mit, Quantized.

  2-bit   Apple-silicon Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek   Deepseek v41   Mlx   Moe   Mtplx   Q2   Quantized   Region:us   Safetensors   Streaming
Model Card on HF 🤗: https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2 

DeepSeek V4.1 Flash MTPLX Streaming Q2 Parameters and Internals

LLM NameDeepSeek V4.1 Flash MTPLX Streaming Q2
Repository 🤗https://huggingface.co/OpensourceWTF/DeepSeek-V4.1-Flash-MTPLX-streaming-q2 
Base Model(s)  deepseek-ai/DeepSeek-V4.1-Flash   deepseek-ai/DeepSeek-V4.1-Flash
Model Size22.7b
Required VRAM0.2 GB
Updated2026-09-13
MaintainerOpensourceWTF
Model Typedeepseek_v41
Model Files  170.0 GB   0.5 GB   0.7 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB   0.2 GB
Quantization Typeq2
Model ArchitectureDeepseekV41ForCausalLM
Licensemit
Transformers Version5.6.0