LLM EXPLORER 63,069 MODELS INDEXED

Qwen3.8 Flash Next MLX Serve IQ MLX 4.7bpw by ddalcu

By ddalcu · 399 downloads
HF Repo ↗ Copy URL

Qwen3.8 Flash Next MLX Serve IQ MLX 4.7bpw is an open-source language model by ddalcu. Features: 133.2b LLM, VRAM: 0.1GB, License: other, LLM Explorer Score: 0.33.

  4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3.8-flash-...   Conversational   Mlx   Mlx-serve   Moe   Ngram-embedding   Qwen4 exp   Region:us   Safetensors   Sparse-attention
Model Card on HF 🤗: https://huggingface.co/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-4.7bpw 

Qwen3.8 Flash Next MLX Serve IQ MLX 4.7bpw Parameters and Internals

LLM NameQwen3.8 Flash Next MLX Serve IQ MLX 4.7bpw
Repository 🤗https://huggingface.co/ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-4.7bpw 
Base Model(s)  Qwen/Qwen3.8-Flash-Next   Qwen/Qwen3.8-Flash-Next
Model Size133.2b
Required VRAM0.1 GB
Updated2026-10-05
Maintainerddalcu
Model Typeqwen4_exp
Model Files  0.1 GB   0.9 GB   0.6 GB   0.9 GB   0.5 GB   0.1 GB   0.9 GB   0.5 GB   0.9 GB   0.6 GB   0.9 GB   0.6 GB   0.9 GB   0.6 GB   0.9 GB   0.5 GB   0.9 GB   0.6 GB   0.9 GB   0.6 GB   0.9 GB   0.6 GB   0.9 GB   0.5 GB   0.9 GB   0.6 GB   0.9 GB   0.5 GB   1.0 GB   0.9 GB   1.0 GB   0.9 GB   0.6 GB   0.9 GB   0.5 GB   0.9 GB   0.6 GB   0.9 GB   0.6 GB   0.9 GB   0.6 GB   0.9 GB   0.5 GB
Model ArchitectureQwen4ExpForConditionalGeneration
Licenseother
Transformers Version5.8.0.dev0

Best Alternatives to Qwen3.8 Flash Next MLX Serve IQ MLX 4.7bpw

Best Alternatives
Context / RAM
Downloads
Likes
...Next Uncensored MLX Serve 4bit0K / 0.1 GB862220
...ensored MLX Serve Mixed 4 8bit0K / 0.1 GB6381
Note: green Score (e.g. "73.2") means that the model is better than ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-4.7bpw.