LLM EXPLORER 58,744 MODELS INDEXED

Qwen3.8 27B AWQ FP8 by cyankiwi

By cyankiwi · 1310 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B AWQ FP8 is an open-source language model by cyankiwi. Features: 27b LLM, VRAM: 31.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.36.

  Awq Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   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/Qwen3.8-27B-AWQ-FP8 

Qwen3.8 27B AWQ FP8 Parameters and Internals

LLM NameQwen3.8 27B AWQ FP8
Repository 🤗https://huggingface.co/cyankiwi/Qwen3.8-27B-AWQ-FP8 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM31.4 GB
Updated2026-08-17
Maintainercyankiwi
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-7   5.0 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   3.9 GB: 7-of-7
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B AWQ FP8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.8 27B AWQ INT40K / 21 GB2101532
Qwen3.6 27B AWQ INT40K / 20.4 GB2563390103
Qwen3.8 27B AWQ 4bit0K / 27.7 GB118746
Qwen3.8 27B W4A16 AWQ0K / 0.8 GB34137
Qwen3.8 27B AWQ 4.85bpw0K / 16.8 GB8758
Qwen3.6 27B AWQ0K / 22 GB66892424
Qwen3.6 27B AWQ BF16 INT40K / 28.3 GB41917141
...en3.8 27B Quark AWQ INT4 W4A160K / 19.5 GB14892
Qwen3.6 27B AWQ 4bit0K / 18.7 GB665563
...wen3.6 27B Abliterated AWQ MTP0K / 18.4 GB24497812
Note: green Score (e.g. "73.2") means that the model is better than cyankiwi/Qwen3.8-27B-AWQ-FP8.