LLM EXPLORER 58,531 MODELS INDEXED

Qwen3.8 27B 3bit MLX TextOnly by lukaskremla

By lukaskremla · 218 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B 3bit MLX TextOnly is an open-source language model by lukaskremla. Features: 27b LLM, VRAM: 11.8GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  3-bit   3bit   Affine Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Group-size-64   Long-context   Mlx   Mlx-lm   Multilingual   Quantized   Qwen   Qwen3.8   Qwen3.8-27b   Qwen3 5   Reasoning   Region:us   Rtn   Safetensors   Sharded   Tensorflow   Text-only   Tool-use   Weight-only-quantization
Model Card on HF 🤗: https://huggingface.co/lukaskremla/Qwen3.8-27B-3bit-MLX-TextOnly 

Qwen3.8 27B 3bit MLX TextOnly Parameters and Internals

LLM NameQwen3.8 27B 3bit MLX TextOnly
Repository 🤗https://huggingface.co/lukaskremla/Qwen3.8-27B-3bit-MLX-TextOnly 
Model NameQwen3.8-27B 3-bit MLX Text-Only
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM11.8 GB
Updated2026-08-15
Maintainerlukaskremla
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.4 GB: 2-of-3   1.1 GB: 3-of-3
Quantization Type3bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B 3bit MLX TextOnly

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Qwen3.8 27B 4bit0K / 16 GB605527
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B MLX 4bit0K / 16 GB1971210
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
...X Qwen3.8 27B MLX AXQ 6bit MTP0K / 19 GB10885
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
...X Qwen3.8 27B MLX AXQ 4bit MTP0K / 16.4 GB5542
Note: green Score (e.g. "73.2") means that the model is better than lukaskremla/Qwen3.8-27B-3bit-MLX-TextOnly.