LLM EXPLORER 58,297 MODELS INDEXED

Qwen3.6 27B Akka 6bit MLX by philipjohnbasile

By philipjohnbasile · 78 downloads
HF Repo ↗ Copy URL

Qwen3.6 27B Akka 6bit MLX is an open-source language model by philipjohnbasile. Features: 27b LLM, VRAM: 21.8GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.31.

  6-bit   6bit   Apple-silicon Base model:nightmedia/qwen3.6-... Base model:quantized:nightmedi...   Conversational   En   Es   Fable   Ja   Mlx   Quantized   Qwen   Qwen3.5   Qwen3.6   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow   Tess   Zh
Model Card on HF 🤗: https://huggingface.co/philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX 

Qwen3.6 27B Akka 6bit MLX Parameters and Internals

LLM NameQwen3.6 27B Akka 6bit MLX
Repository 🤗https://huggingface.co/philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX 
Base Model(s)  nightmedia/Qwen3.6-27B-Akka   nightmedia/Qwen3.6-27B-Akka
Model Size27b
Required VRAM21.8 GB
Updated2026-08-13
Maintainerphilipjohnbasile
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-5   5.3 GB: 2-of-5   5.3 GB: 3-of-5   4.8 GB: 4-of-5   1.0 GB: 5-of-5
Supported Languagesen zh ja es
Quantization Type6bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.14.1
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.6 27B Akka 6bit MLX

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
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
...27B Turkish Legal LLM Mlx 4Bit0K / 15.1 GB36625
Qwen3.6 27B 4bit0K / 16 GB4367249
...inkingCap Qwen3.6 27B Mlx 6Bit0K / 21.8 GB34746
...kingCap Qwen3.6 27B OptiQ 4bit0K / 18.7 GB23553
Note: green Score (e.g. "73.2") means that the model is better than philipjohnbasile/Qwen3.6-27B-Akka-6bit-MLX.