LLM EXPLORER 61,652 MODELS INDEXED

Swift Qwen3.8 27B OQ4 Mtp by suzu89

By suzu89 · 226 downloads
HF Repo ↗ Copy URL

Swift Qwen3.8 27B OQ4 Mtp is an open-source language model by suzu89. Features: 27b LLM, VRAM: 16.9GB, License: other, LLM Explorer Score: 0.32.

  4-bit   Apple-silicon Base model:quantized:ukisai/sw... Base model:ukisai/swift-qwen3....   Base model size:10b to 100b   Conversational   Image-text-to-text   Mixed-precision   Mlx   Mtp   Omlx   Quantization   Qwen   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ4-mtp 

Swift Qwen3.8 27B OQ4 Mtp Parameters and Internals

LLM NameSwift Qwen3.8 27B OQ4 Mtp
Repository 🤗https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ4-mtp 
Model NameSwift-Qwen3.8-27b-oQ4-mtp
Base Model(s)  ukisai/Swift-Qwen3.8-27b   ukisai/Swift-Qwen3.8-27b
Model Size27b
Required VRAM16.9 GB
Updated2026-09-19
Maintainersuzu89
Model Typeqwen3_5
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.9 GB: 4-of-4
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 OQ4 Mtp

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1451
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.6 27B FP80K / 0.4 GB7740472342
Qwen3.5 27B0K / 55.2 GB25362941028
Note: green Score (e.g. "73.2") means that the model is better than suzu89/Swift-Qwen3.8-27b-oQ4-mtp.