LLM EXPLORER 61,836 MODELS INDEXED

Gemma 3 27B It GPTQ 4B 128g by ISTA-DASLab

By ISTA-DASLab · 303597 downloads
HF Repo ↗ Copy URL

Gemma 3 27B It GPTQ 4B 128g is an open-source language model by ISTA-DASLab. Features: 27b LLM, VRAM: 16.9GB, License: gemma, Quantized, LLM Explorer Score: 0.26.

Base model:google/gemma-3-27b-... Base model:quantized:google/ge...   Compressed-tensors   Conversational   Endpoints compatible   Gemma3   Gptq   Image-text-to-text   Int4   Llmcompressor   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g 

Gemma 3 27B It GPTQ 4B 128g Parameters and Internals

LLM NameGemma 3 27B It GPTQ 4B 128g
Repository 🤗https://huggingface.co/ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g 
Base Model(s)  Gemma 3 27B It   google/gemma-3-27b-it
Model Size27b
Required VRAM16.9 GB
Updated2026-08-08
MaintainerISTA-DASLab
Model Typegemma3
Model Files  3.4 GB: 1-of-5   3.4 GB: 2-of-5   3.4 GB: 3-of-5   3.0 GB: 4-of-5   3.7 GB: 5-of-5
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureGemma3ForConditionalGeneration
Licensegemma
Transformers Version4.50.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16

Best Alternatives to Gemma 3 27B It GPTQ 4B 128g

Best Alternatives
Context / RAM
Downloads
Likes
...emma 3 27B It Unsloth Bnb 4bit0K / 20.2 GB552519
Gemma 3 27B It Bnb 4bit0K / 16.3 GB274418
... 3 27B It Qat Q4 0 Unquantized0K / 55.3 GB15242
Gemma 3 27B It Qat0K / 55.3 GB243
Translategemma 27B It 8bit0K / 28.8 GB4675
Translategemma 27B It 4bit0K / 15.2 GB1903
Medgemma 27B It 8bit0K / 31.2 GB1994
Medgemma 27B It 4bit0K / 16.9 GB1324
Gemma 3 27B It 4bit0K / 16.9 GB157813
Gemma 3 27B It 4bit DWQ0K / 16 GB863
Note: green Score (e.g. "73.2") means that the model is better than ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g.