LLM EXPLORER 62,751 MODELS INDEXED

Swift Qwen3.8 27B Int8 W8a16 Dflash2 by auggie246

By auggie246 · 47 downloads
HF Repo ↗ Copy URL

Swift Qwen3.8 27B Int8 W8a16 Dflash2 is an open-source language model by auggie246. Features: 27b LLM, VRAM: 29.6GB, License: other, LLM Explorer Score: 0.28.

Base model:quantized:ukisai/sw... Base model:ukisai/swift-qwen3....   Compressed-tensors   Conversational   Dflash   Efficient-thinking   Image-text-to-text   Int8   Multimodal   Quantized   Qwen3 5   Qwen3 8   Reasoning   Region:us   Safetensors   Sharded   Tensorflow   Token-efficient   Vllm   W8a16
Model Card on HF 🤗: https://huggingface.co/auggie246/swift-qwen3.8-27b-int8-w8a16-dflash2 

Swift Qwen3.8 27B Int8 W8a16 Dflash2 Parameters and Internals

LLM NameSwift Qwen3.8 27B Int8 W8a16 Dflash2
Repository 🤗https://huggingface.co/auggie246/swift-qwen3.8-27b-int8-w8a16-dflash2 
Base Model(s)  ukisai/Swift-Qwen3.8-27b   ukisai/Swift-Qwen3.8-27b
Model Size27b
Required VRAM29.6 GB
Updated2026-10-02
Maintainerauggie246
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.3 GB: 3-of-6   5.4 GB: 4-of-6   5.4 GB: 5-of-6   2.9 GB: 6-of-6
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Swift Qwen3.8 27B Int8 W8a16 Dflash2

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1112
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.5 27B0K / 55.2 GB25362941028
Qwen3.6 27B FP80K / 0.4 GB7740472342
Note: green Score (e.g. "73.2") means that the model is better than auggie246/swift-qwen3.8-27b-int8-w8a16-dflash2.