LLM EXPLORER 60,384 MODELS INDEXED

Qwen3.5 27B AWQ by QuantTrio

By QuantTrio · 370920 downloads
HF Repo ↗ Copy URL

Qwen3.5 27B AWQ is an open-source language model by QuantTrio. Features: 27b LLM, VRAM: 21.9GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.34.

  4-bit   Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.5-27b   Conversational   Endpoints compatible   Image-text-to-text   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/QuantTrio/Qwen3.5-27B-AWQ 

Qwen3.5 27B AWQ Parameters and Internals

LLM NameQwen3.5 27B AWQ
Repository 🤗https://huggingface.co/QuantTrio/Qwen3.5-27B-AWQ 
Base Model(s)  Qwen/Qwen3.5-27B   Qwen/Qwen3.5-27B
Model Size27b
Required VRAM21.9 GB
Updated2026-09-04
MaintainerQuantTrio
Model Typeqwen3_5
Model Files  3.0 GB: 1-of-8   3.0 GB: 2-of-8   3.0 GB: 3-of-8   3.0 GB: 4-of-8   3.0 GB: 5-of-8   2.6 GB: 6-of-8   2.9 GB: 7-of-8   1.4 GB: 8-of-8
AWQ QuantizationYes
Quantization Typeawq
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 27B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B AWQ INT40K / 20.4 GB2563390103
Qwen3.8 27B AWQ INT40K / 21 GB2101532
Qwen3.6 27B AWQ0K / 22 GB66892424
Qwen3.6 27B AWQ BF16 INT40K / 28.3 GB41917141
Qwen3.8 27B AWQ 4bit0K / 27.7 GB118746
...wen3.6 27B Abliterated AWQ MTP0K / 18.4 GB24497812
...wen3.8 27B Abliterated AWQ MTP0K / 19.1 GB44948
Qwen3.8 27B AWQ 5.0bpw0K / 17.3 GB144520
Qwen3.5 27B AWQ 4bit0K / 20 GB27906442
Qwen3.8 27B W4A16 AWQ0K / 0.8 GB34137
Note: green Score (e.g. "73.2") means that the model is better than QuantTrio/Qwen3.5-27B-AWQ.