LLM EXPLORER 62,007 MODELS INDEXED

Swift Qwen3.8 27B MLX 6bit by majentik

By majentik · 236 downloads
HF Repo ↗ Copy URL

Swift Qwen3.8 27B MLX 6bit is an open-source language model by majentik. Features: 27b LLM, VRAM: 22.7GB, License: other, Quantized, LLM Explorer Score: 0.32.

  6-bit   6bit Base model:quantized:ukisai/sw... Base model:ukisai/swift-qwen3....   Conversational   Image-text-to-text   Mlx   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/majentik/Swift-Qwen3.8-27B-MLX-6bit 

Swift Qwen3.8 27B MLX 6bit Parameters and Internals

LLM NameSwift Qwen3.8 27B MLX 6bit
Repository 🤗https://huggingface.co/majentik/Swift-Qwen3.8-27B-MLX-6bit 
Base Model(s)  ukisai/Swift-Qwen3.8-27b   ukisai/Swift-Qwen3.8-27b
Model Size27b
Required VRAM22.7 GB
Updated2026-09-23
Maintainermajentik
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-5   5.3 GB: 2-of-5   5.3 GB: 3-of-5   5.3 GB: 4-of-5   1.4 GB: 5-of-5
Quantization Type6bit
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 MLX 6bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B MLX 5bit0K / 19.5 GB46750442
...onsai 2 27B CRACK Ternary JANG0K / 8.1 GB268913
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.8 27B 8bit0K / 29.4 GB1389233
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
Ternary Bonsai 2 27B Vllm0K / 10.3 GB20484
Note: green Score (e.g. "73.2") means that the model is better than majentik/Swift-Qwen3.8-27B-MLX-6bit.