LLM EXPLORER 60,958 MODELS INDEXED

DeepSeek V4.1 Flash MLX Mixed 4 8bit Engram6 by pipenetwork

By pipenetwork · 1072 downloads

DeepSeek V4.1 Flash MLX Mixed 4 8bit Engram6 is an open-source language model by pipenetwork. Features: 428b LLM, VRAM: 7.9GB, License: mit, Quantized.

  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

DeepSeek V4.1 Flash MLX Mixed 4 8bit Engram6 Parameters and Internals

LLM NameDeepSeek V4.1 Flash MLX Mixed 4 8bit Engram6
Repository πŸ€—https://huggingface.co/pipenetwork/DeepSeek-V4.1-Flash-MLX-mixed-4_8bit-engram6 
Base Model(s)  deepseek-ai/DeepSeek-V4.1-Flash   deepseek-ai/DeepSeek-V4.1-Flash
Model Size428b
Required VRAM7.9 GB
Updated2026-09-13
Maintainerpipenetwork
Model Typedeepseek_v41
Model Files  7.9 GB   79.9 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   79.9 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