LLM EXPLORER 66,704 MODELS INDEXED

DeepSeek V4.1 Flash MLX Mixed 4 8bit by pipenetwork

By pipenetwork · 1977 downloads
HF Repo ↗ Copy URL

DeepSeek V4.1 Flash MLX Mixed 4 8bit is an open-source language model by pipenetwork. Features: 378.9b LLM, VRAM: 7.9GB, License: mit, Quantized, LLM Explorer Score: 0.3.

  4-bit   8bit   Apple-silicon Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-...   Deepseek v41   Fp8   Mixture-of-experts   Mlx   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/pipenetwork/DeepSeek-V4.1-Flash-MLX-mixed-4_8bit 

DeepSeek V4.1 Flash MLX Mixed 4 8bit Parameters and Internals

LLM NameDeepSeek V4.1 Flash MLX Mixed 4 8bit
Repository 🤗https://huggingface.co/pipenetwork/DeepSeek-V4.1-Flash-MLX-mixed-4_8bit 
Base Model(s)  deepseek-ai/DeepSeek-V4.1-Flash   deepseek-ai/DeepSeek-V4.1-Flash
Model Size378.9b
Required VRAM7.9 GB
Updated2026-09-13
Maintainerpipenetwork
Model Typedeepseek_v41
Model Files  7.9 GB   55.3 GB   8.0 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   55.3 GB   8.0 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB   7.9 GB
Quantization Type8bit
Model ArchitectureDeepseekV41ForCausalLM
Licensemit
Transformers Version5.6.0

Best Alternatives to DeepSeek V4.1 Flash MLX Mixed 4 8bit

Best Alternatives
Context / RAM
Downloads
Likes
....1 Flash 1017 MLX Mixed 4 8bit0K / 7.9 GB9552
Note: green Score (e.g. "73.2") means that the model is better than pipenetwork/DeepSeek-V4.1-Flash-MLX-mixed-4_8bit.