LLM EXPLORER 61,060 MODELS INDEXED

Qwen3.8 27B MLX AD 3.70bpw DWQ 13.4GB by AtomicChat

By AtomicChat · 964 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B MLX AD 3.70bpw DWQ 13.4GB is an open-source language model by AtomicChat. Features: 27b LLM, VRAM: 13.4GB, LLM Explorer Score: 0.31.

  4-bit   Conversational   En   Image-text-to-text   Mlx   Qwen3 5   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/AtomicChat/Qwen3.8-27B-MLX-AD-3.70bpw-DWQ-13.4GB 

Qwen3.8 27B MLX AD 3.70bpw DWQ 13.4GB Parameters and Internals

LLM NameQwen3.8 27B MLX AD 3.70bpw DWQ 13.4GB
Repository 🤗https://huggingface.co/AtomicChat/Qwen3.8-27B-MLX-AD-3.70bpw-DWQ-13.4GB 
Model Size27b
Required VRAM13.4 GB
Updated2026-09-13
MaintainerAtomicChat
Model Typeqwen3_5
Model Files  13.4 GB
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B MLX AD 3.70bpw DWQ 13.4GB

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB1321
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.6 27B NVFP40K / 22 GB1887525419
Qwen3.8 27B NVFP40K / 22 GB1919574
Qwen3.6 27B FP80K / 0.4 GB7740472342
Note: green Score (e.g. "73.2") means that the model is better than AtomicChat/Qwen3.8-27B-MLX-AD-3.70bpw-DWQ-13.4GB.