LLM EXPLORER 62,076 MODELS INDEXED

MiMo V2.6 Distill Qwen 9B MLX 4bit by nativ-community

By nativ-community · 406 downloads

MiMo V2.6 Distill Qwen 9B MLX 4bit is an open-source language model by nativ-community. Features: 9b LLM, VRAM: 5.9GB, Quantized, LLM Explorer Score: 0.33.

  4-bit   4bit   Agentic Base model:finetune:xiaomimimo... Base model:xiaomimimo/mimo-v2....   Code   Conversational   Distillation   Image-text-to-text   Mimo v2   Mlx   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Supervised-fine-tuning   Tensorflow   Tool-use

MiMo V2.6 Distill Qwen 9B MLX 4bit Parameters and Internals

LLM NameMiMo V2.6 Distill Qwen 9B MLX 4bit
Repository πŸ€—https://huggingface.co/nativ-community/MiMo-V2.6-Distill-Qwen-9B-MLX-4bit 
Base Model(s)  XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B   XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Model Size9b
Required VRAM5.9 GB
Updated2026-09-24
Maintainernativ-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-2   0.6 GB: 2-of-2
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to MiMo V2.6 Distill Qwen 9B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...2.6 Distill Qwen 9B OptiQ 4bit0K / 7.1 GB19166
Qwen3.5 9B MLX 4bit0K / 5.9 GB5800124
Qwen3.5 9B MLX 8bit0K / 10.4 GB5504971
Ornith 1.5 9B MLX 4bit0K / 5 GB304318
... V2.6 Distill Qwen 9B MLX 8bit0K / 10.4 GB3751
...Distill Qwen 9B MLX Serve 6bit0K / 0.2 GB3071
Ornith 1.5 9B MLX 8bit0K / 9.5 GB26867
Qwen3.5 9B MLX 4bit0K / 5.9 GB22827151
Ornith 1.0 9B 4bit0K / 5.9 GB97919
Qwen3.5 9B 8bit0K / 10.4 GB4565217
Note: green Score (e.g. "73.2") means that the model is better than nativ-community/MiMo-V2.6-Distill-Qwen-9B-MLX-4bit.