LLM EXPLORER 59,278 MODELS INDEXED

Qwen3.8 27B GPTQ Pro 4bit G64 Calib128 by groxaxo

By groxaxo · 182 downloads
HF Repo ↗ Copy URL

Qwen3.8 27B GPTQ Pro 4bit G64 Calib128 is an open-source language model by groxaxo. Features: 27b LLM, VRAM: 20.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.31.

  4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.8-27b   Conversational   Endpoints compatible   Gptq   Gptq-pro   Image-text-to-text   Mtp   Quantized   Qwen3.5-architecture   Qwen3.8   Qwen3 5   Region:us   Safetensors   Sharded   Speculative-decoding   Tensorflow
Model Card on HF 🤗: https://huggingface.co/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128 

Qwen3.8 27B GPTQ Pro 4bit G64 Calib128 Parameters and Internals

LLM NameQwen3.8 27B GPTQ Pro 4bit G64 Calib128
Repository 🤗https://huggingface.co/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128 
Base Model(s)  Qwen/Qwen3.8-27B   Qwen/Qwen3.8-27B
Model Size27b
Required VRAM20.1 GB
Updated2026-08-22
Maintainergroxaxo
Model Typeqwen3_5
Model Files  3.5 GB: 1-of-5   4.3 GB: 2-of-5   4.3 GB: 3-of-5   4.3 GB: 4-of-5   3.7 GB: 5-of-5
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.15.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Qwen3.8 27B GPTQ Pro 4bit G64 Calib128

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B GPTQ Pro 4bit0K / 18.8 GB41540739
...en3.8 27B W4A16 AutoRound GPTQ0K / 19.2 GB37485
Qwen3.8 27B GPTQ 4bit0K / 21 GB24335
Qwen3.8 27B GPTQ Int40K / 20.2 GB22673
Qwen3.5 27B GPTQ Int40K / 30.1 GB10538157
Qwen3.8 27B GPTQ INT4 G1280K / 19.6 GB4683
...7B GPTQ Int4 Sym G128 MTP BF160K / 19.6 GB5363
Qwen3.8 27B GPTQ Int40K / 19.6 GB8811
Qwen3.8 27B GPTQ INT4 G320K / 21 GB1363
Qwen3.8 27B GPTQ INT80K / 31.9 GB1402
Note: green Score (e.g. "73.2") means that the model is better than groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128.