LLM EXPLORER 64,924 MODELS INDEXED

Qwen3.8 Flash Next MLX Serve IQ MLX 7.1bpw by xpashkin

By xpashkin · 802 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MLX Serve IQ MLX 7.1bpw is an open-source language model by xpashkin. Features: 135.2b LLM, VRAM: 0.1GB, License: other, LLM Explorer Score: 0.32.

  6-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Imatrix   Mlx   Mlx-serve   Moe   Ngram-embedding   Qwen4 exp   Region:us   Safetensors   Sparse-attention
Model Card on HF 🤗: https://huggingface.co/xpashkin/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-7.1bpw 

Qwen3.8 Flash Next MLX Serve IQ MLX 7.1bpw Parameters and Internals

LLM NameQwen3.8 Flash Next MLX Serve IQ MLX 7.1bpw
Repository 🤗https://huggingface.co/xpashkin/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-7.1bpw 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size135.2b
Required VRAM0.1 GB
Updated2026-10-19
Maintainerxpashkin
Model Typeqwen4_exp
Model Files  0.1 GB   1.4 GB   0.8 GB   1.4 GB   0.8 GB   0.1 GB   1.4 GB   0.7 GB   1.4 GB   0.9 GB   1.4 GB   0.8 GB   1.4 GB   0.8 GB   1.4 GB   0.7 GB   1.4 GB   0.9 GB   1.4 GB   0.8 GB   1.4 GB   0.8 GB   1.4 GB   0.7 GB   1.8 GB   0.9 GB   1.4 GB   0.7 GB   1.5 GB   1.8 GB   1.5 GB   1.4 GB   0.8 GB   1.4 GB   0.7 GB   1.8 GB   0.9 GB   1.4 GB   0.8 GB   1.4 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0

Best Alternatives to Qwen3.8 Flash Next MLX Serve IQ MLX 7.1bpw

Best Alternatives
Context / RAM
Downloads
Likes
...lash Next W4A16 PLE4 MTP Spark0K / 0.1 GB392