LLM EXPLORER 66,845 MODELS INDEXED

Qwen3.5 9B AWQ 4bit by cyankiwi

By cyankiwi · 214142 downloads
HF Repo ↗ Copy URL

Qwen3.5 9B AWQ 4bit is an open-source language model by cyankiwi. Features: 9b LLM, VRAM: 9.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  4bit   Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.5-9b   Compressed-tensors   Conversational   Endpoints compatible   Image-text-to-text   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cyankiwi/Qwen3.5-9B-AWQ-4bit 

Qwen3.5 9B AWQ 4bit Parameters and Internals

LLM NameQwen3.5 9B AWQ 4bit
Repository 🤗https://huggingface.co/cyankiwi/Qwen3.5-9B-AWQ-4bit 
Base Model(s)  Qwen/Qwen3.5-9B   Qwen/Qwen3.5-9B
Model Size9b
Required VRAM9.1 GB
Updated2026-08-09
Maintainercyankiwi
Model Typeqwen3_5
Model Files  3.5 GB: 1-of-3   5.4 GB: 2-of-3   0.2 GB: 3-of-3
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.5 9B AWQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 9B AWQ0K / 12.4 GB128558224
Ornith 1.5 9B AWQ INT40K / 9 GB32991
Qwen3.5 9B AWQ 8bit0K / 0.5 GB273
Qwen3.5 9B AWQ 4bit0K / 0.5 GB271
... Distill Qwen 9B AWQ BF16 INT40K / 9 GB1821
Qwen3.5 9B MLX 4bit0K / 5.9 GB5800124
Qwen3.5 9B MLX 8bit0K / 10.4 GB5504971
Qwen3.5 9B MLX 4bit0K / 5.9 GB22827151
...2.6 Distill Qwen 9B OptiQ 4bit0K / 7.1 GB19166
Ornith 1.5 9B MLX 4bit0K / 5 GB304318
Note: green Score (e.g. "73.2") means that the model is better than cyankiwi/Qwen3.5-9B-AWQ-4bit.