LLM EXPLORER 63,407 MODELS INDEXED

Swift 1.5 Qwen3.8 27B NVFP4 by jessedye90

By jessedye90 · 77 downloads
HF Repo ↗ Copy URL

Swift 1.5 Qwen3.8 27B NVFP4 is an open-source language model by jessedye90. Features: 27b LLM, VRAM: 21.1GB, License: other, LLM Explorer Score: 0.28.

  8-bit Base model:quantized:ukisai/sw... Base model:ukisai/swift-1.5-qw...   Blackwell   Conversational   Dflash2   Dgx-spark   Efficient-thinking   Endpoints compatible   Fp8   Image-text-to-text   Modelopt   Nvfp4   Qwen3 5   Qwen3 8   Reasoning   Region:us   Safetensors   Sglang   Sharded   Speculative-decoding   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jessedye90/Swift-1.5-Qwen3.8-27B-NVFP4 

Swift 1.5 Qwen3.8 27B NVFP4 Parameters and Internals

LLM NameSwift 1.5 Qwen3.8 27B NVFP4
Repository 🤗https://huggingface.co/jessedye90/Swift-1.5-Qwen3.8-27B-NVFP4 
Base Model(s)  ukisai/Swift-1.5-Qwen3.8-27b   ukisai/Swift-1.5-Qwen3.8-27b
Model Size27b
Required VRAM21.1 GB
Updated2026-10-08
Maintainerjessedye90
Model Typeqwen3_5
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   1.1 GB: 3-of-3
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseother
Model Max Length262144
Transformers Version5.12.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Swift 1.5 Qwen3.8 27B NVFP4

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB873
Qwen3.8 27B NPU2256K /  GB2524
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB95131835
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B FP80K / 0.4 GB123157416
Note: green Score (e.g. "73.2") means that the model is better than jessedye90/Swift-1.5-Qwen3.8-27B-NVFP4.