LLM EXPLORER 58,531 MODELS INDEXED

AX Qwen3.8 27B MLX AXQ 4bit MTP by AutomatosX

By AutomatosX · 554 downloads
HF Repo ↗ Copy URL

AX Qwen3.8 27B MLX AXQ 4bit MTP is an open-source language model by AutomatosX. Features: 27b LLM, VRAM: 16.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.34.

  4-bit   4bit   Apple-silicon   Axq   Axquant Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Development   Mixed-precision   Mlx   Mtp   Quantized   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow   Vision
Model Card on HF 🤗: https://huggingface.co/AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP 

AX Qwen3.8 27B MLX AXQ 4bit MTP Parameters and Internals

LLM NameAX Qwen3.8 27B MLX AXQ 4bit MTP
Repository 🤗https://huggingface.co/AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM16.4 GB
Updated2026-08-15
MaintainerAutomatosX
Model Typeqwen3_5
Model Files  5.4 GB: 1-of-4   5.3 GB: 2-of-4   4.3 GB: 3-of-4   1.4 GB: 4-of-4   0.8 GB   0.9 GB
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to AX Qwen3.8 27B MLX AXQ 4bit MTP

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
AX Qwen3.8 27B MLX AXQ 6bit0K / 19.6 GB5501
Note: green Score (e.g. "73.2") means that the model is better than AutomatosX/AX-Qwen3.8-27B-MLX-AXQ-4bit-MTP.