LLM EXPLORER 62,404 MODELS INDEXED

MiMo V2.6 Distill Qwen 9B AWQ BF16 INT4 by cyankiwi

By cyankiwi · 182 downloads
HF Repo ↗ Copy URL

MiMo V2.6 Distill Qwen 9B AWQ BF16 INT4 is an open-source language model by cyankiwi. Features: 9b LLM, VRAM: 9GB, License: mit, Quantized, LLM Explorer Score: 0.31.

  Agentic   Awq Base model:quantized:xiaomimim... Base model:xiaomimimo/mimo-v2....   Code   Compressed-tensors   Conversational   Distillation   Endpoints compatible   Image-text-to-text   Mimo v2   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Supervised-fine-tuning   Tensorflow   Tool-use
Model Card on HF 🤗: https://huggingface.co/cyankiwi/MiMo-V2.6-Distill-Qwen-9B-AWQ-BF16-INT4 

MiMo V2.6 Distill Qwen 9B AWQ BF16 INT4 Parameters and Internals

LLM NameMiMo V2.6 Distill Qwen 9B AWQ BF16 INT4
Repository 🤗https://huggingface.co/cyankiwi/MiMo-V2.6-Distill-Qwen-9B-AWQ-BF16-INT4 
Base Model(s)  XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B   XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B
Model Size9b
Required VRAM9 GB
Updated2026-09-28
Maintainercyankiwi
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-2   4.0 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5ForConditionalGeneration
Licensemit
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to MiMo V2.6 Distill Qwen 9B AWQ BF16 INT4

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 9B AWQ0K / 12.4 GB128558224
Qwen3.5 9B AWQ 4bit0K / 9.1 GB21414235
Ornith 1.5 9B AWQ INT40K / 9 GB32991
Qwen3.5 9B MLX 4bit0K / 5.9 GB5800124
Qwen3.5 9B MLX 8bit0K / 10.4 GB5504971
...2.6 Distill Qwen 9B OptiQ 4bit0K / 7.1 GB19166
LensVLM 9B OptiQ 4bit0K / 7.1 GB2425
Ornith 1.5 9B MLX 4bit0K / 5 GB304318
... V2.6 Distill Qwen 9B MLX 4bit0K / 5.9 GB4062
Qwen3.5 9B MLX 4bit0K / 5.9 GB22827151
Note: green Score (e.g. "73.2") means that the model is better than cyankiwi/MiMo-V2.6-Distill-Qwen-9B-AWQ-BF16-INT4.