LLM EXPLORER 62,323 MODELS INDEXED

Swift 1.5 Qwen3.8 27B W4A16 AWQ by ukisai

By ukisai · 514 downloads
HF Repo ↗ Copy URL

Swift 1.5 Qwen3.8 27B W4A16 AWQ is an open-source language model by ukisai. Features: 27b LLM, VRAM: 18.7GB, License: other, Quantized, LLM Explorer Score: 0.32.

  Awq Base model:quantized:ukisai/sw... Base model:ukisai/swift-1.5-qw...   Compressed-tensors   Conversational   Efficient-thinking   Endpoints compatible   Image-text-to-text   Post-training   Quantized   Qwen3 5   Qwen3 8   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Terminal-bench   Token-efficient
Model Card on HF 🤗: https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b-W4A16-AWQ 

Swift 1.5 Qwen3.8 27B W4A16 AWQ Parameters and Internals

LLM NameSwift 1.5 Qwen3.8 27B W4A16 AWQ
Repository 🤗https://huggingface.co/ukisai/Swift-1.5-Qwen3.8-27b-W4A16-AWQ 
Base Model(s)  ukisai/Swift-1.5-Qwen3.8-27b   ukisai/Swift-1.5-Qwen3.8-27b
Model Size27b
Required VRAM18.7 GB
Updated2026-09-27
Maintainerukisai
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-6   4.0 GB: 2-of-6   4.0 GB: 3-of-6   4.0 GB: 4-of-6   4.0 GB: 5-of-6   0.2 GB: 6-of-6   0.8 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Swift 1.5 Qwen3.8 27B W4A16 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
...ingCap Qwen3.8 27B NVFP4A4 AWQ0K / 22.5 GB22410
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
Qwen3.8 27B AWQ W4A16 ASYM0K / 0.8 GB134843
Qwen3.5 27B AWQ 4bit0K / 20 GB27906442
Note: green Score (e.g. "73.2") means that the model is better than ukisai/Swift-1.5-Qwen3.8-27b-W4A16-AWQ.