LLM EXPLORER 66,613 MODELS INDEXED

Qwen3.8 27B GPTQ 4bit by mlx-community

By mlx-community · 278 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B GPTQ 4bit is an open-source language model by mlx-community. Features: 27b LLM, VRAM: 16GB, License: apache-2.0, Quantized.

  4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Gptq   Image-text-to-text   Mlx   Quantized   Qwen3 5   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3.8-27B-GPTQ-4bit 

Qwen3.8 27B GPTQ 4bit Parameters and Internals

LLM NameQwen3.8 27B GPTQ 4bit
Repository 🤗https://huggingface.co/mlx-community/Qwen3.8-27B-GPTQ-4bit 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM16 GB
Updated2026-11-04
Maintainermlx-community
Model Typeqwen3_5
Model Files  5.3 GB: 1-of-3   5.3 GB: 2-of-3   5.4 GB: 3-of-3
GPTQ QuantizationYes
Quantization Typegptq|4bit
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 GPTQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B GPTQ Pro 4bit0K / 18.8 GB41540739
Qwen3.5 27B GPTQ Int40K / 30.1 GB10538157
Qwen3.8 27B GPTQ INT4 FP8KV0K / 20.2 GB64882
...en3.8 27B W4A16 AutoRound GPTQ0K / 19.2 GB37485
Qwen3.8 27B GPTQ 4bit0K / 21 GB24335
Qwen3.8 27B GPTQ Int40K / 20.2 GB22673
Qwen3.8 27B GPTQ Int4 Asym0K / 0.2 GB1581
...3.8 27B Abliterated W4A16 GPTQ0K / 0.8 GB651
Qwen3.8 27B GPTQ Int40K / 19.6 GB8811
Qwen3.8 27B GPTQ INT4 G1280K / 19.6 GB6333
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3.8-27B-GPTQ-4bit.