LLM EXPLORER 67,808 MODELS INDEXED

Qwen3.8 27B MACaQ W4A16 Mlx by mlx-community

By mlx-community · 265 downloads

Qwen3.8 27B MACaQ W4A16 Mlx is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 18GB, License: apache-2.0.

  Arxiv:2611.10649   4-bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Dataset:allenai/c4   Dataset:salesforce/wikitext   En   Macaq   Macaq mxfp4   Mlx   Mxfp4   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow

Qwen3.8 27B MACaQ W4A16 Mlx Parameters and Internals

LLM NameQwen3.8 27B MACaQ W4A16 Mlx
Repository πŸ€—https://huggingface.co/mlx-community/Qwen3.8-27B-MACaQ-W4A16-mlx 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM18 GB
Updated2026-11-19
Maintainermlx-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-4   5.4 GB: 2-of-4   4.8 GB: 3-of-4   2.5 GB: 4-of-4
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B MACaQ W4A16 Mlx

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
Qwen3.6 27B0K / 55.4 GB67281382197
Arete 27B0K / 54.7 GB2407346
Qwen3.8 27B0K / 55.6 GB28753
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.8-27B-MACaQ-W4A16-mlx.