LLM EXPLORER 61,836 MODELS INDEXED

Swift Qwen3.8 27B AWQ INT4 by cyankiwi

By cyankiwi · 249 downloads
HF Repo ↗ Copy URL

Swift Qwen3.8 27B AWQ INT4 is an open-source language model by cyankiwi. Features: 27b LLM, VRAM: 21GB, License: other, Quantized, LLM Explorer Score: 0.31.

  Awq Base model:finetune:ukisai/swi... Base model:ukisai/swift-qwen3....   Compressed-tensors   Conversational   Efficient-thinking   Endpoints compatible   Image-text-to-text   Lora   Quantized   Qwen3 5   Qwen3 8   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Token-efficient
Model Card on HF 🤗: https://huggingface.co/cyankiwi/Swift-Qwen3.8-27B-AWQ-INT4 

Swift Qwen3.8 27B AWQ INT4 Parameters and Internals

LLM NameSwift Qwen3.8 27B AWQ INT4
Repository 🤗https://huggingface.co/cyankiwi/Swift-Qwen3.8-27B-AWQ-INT4 
Base Model(s)  ukisai/Swift-Qwen3.8-27b   ukisai/Swift-Qwen3.8-27b
Model Size27b
Required VRAM21 GB
Updated2026-09-21
Maintainercyankiwi
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-5   5.0 GB: 2-of-5   5.0 GB: 3-of-5   5.0 GB: 4-of-5   3.5 GB: 5-of-5
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
LoRA ModelYes
Errorsreplace

Best Alternatives to Swift Qwen3.8 27B AWQ INT4

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
...wen3.6 27B Abliterated AWQ MTP0K / 18.4 GB24497812
Qwen3.5 27B AWQ0K / 21.9 GB37092044
Qwen3.8 27B AWQ 4bit0K / 27.7 GB118746
Swift Qwen3.8 27B W4A16 AWQ0K / 18.8 GB5956
Qwen3.5 27B AWQ 4bit0K / 20 GB27906442
...wen3.8 27B Abliterated AWQ MTP0K / 19.1 GB44948
Note: green Score (e.g. "73.2") means that the model is better than cyankiwi/Swift-Qwen3.8-27B-AWQ-INT4.