LLM EXPLORER 67,390 MODELS INDEXED

Swift Qwen3.8 27B OQ6 Mtp by suzu89

By suzu89 · 212 downloads
HF Repo ↗ Copy URL

Swift Qwen3.8 27B OQ6 Mtp is an open-source language model by suzu89. Features: 27b LLM, VRAM: 23.6GB, License: other, LLM Explorer Score: 0.26.

  6-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-oQ6-mtp 

Swift Qwen3.8 27B OQ6 Mtp Parameters and Internals

LLM NameSwift Qwen3.8 27B OQ6 Mtp
Repository 🤗https://huggingface.co/suzu89/Swift-Qwen3.8-27b-oQ6-mtp 
Model NameSwift-Qwen3.8-27b-oQ6-mtp
Base Model(s)  ukisai/Swift-Qwen3.8-27b   ukisai/Swift-Qwen3.8-27b
Model Size27b
Required VRAM23.6 GB
Updated2026-09-19
Maintainersuzu89
Model Typeqwen3_5
Model Files  5.1 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
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 OQ6 Mtp

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB863
... 27B 6.3bpw RCO SAR Marlin MTP256K / 22 GB841
Qwen3.8 27B NPU2256K /  GB2524
...toTrust Decider Pro Vision 27B0K / 55.6 GB15373904526
JEV 27B VL0K / 55.6 GB1525286966
Clef0K / 54.7 GB220432237
Arete 27B0K / 54.7 GB2407346
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Note: green Score (e.g. "73.2") means that the model is better than suzu89/Swift-Qwen3.8-27b-oQ6-mtp.