LLM EXPLORER 58,133 MODELS INDEXED

Gemma 3 27B It Qat Q4 0 Unquantized by google

By google · 152 downloads
HF Repo ↗ Copy URL

Gemma 3 27B It Qat Q4 0 Unquantized is an open-source language model by google. Features: 27b LLM, VRAM: 55.3GB, License: gemma, Quantized, LLM Explorer Score: 0.32, ELO: 1366.

  Arxiv:1705.03551   Arxiv:1810.12440   Arxiv:1903.00161   Arxiv:1904.09728   Arxiv:1905.07830   Arxiv:1905.10044   Arxiv:1907.10641   Arxiv:1908.02660   Arxiv:1910.11856   Arxiv:1911.01547   Arxiv:1911.11641   Arxiv:2009.03300   Arxiv:2103.03874   Arxiv:2104.12756   Arxiv:2106.03193   Arxiv:2107.03374   Arxiv:2108.07732   Arxiv:2110.14168   Arxiv:2203.10244   Arxiv:2210.03057   Arxiv:2304.06364   Arxiv:2311.12022   Arxiv:2311.16502   Arxiv:2312.11805   Arxiv:2404.12390   Arxiv:2404.16816   Arxiv:2502.12404   Arxiv:2502.21228 Base model:finetune:google/gem... Base model:google/gemma-3-27b-...   Conversational   Endpoints compatible   Gemma   Gemma3   Google   Image-text-to-text   Q4   Q4 0   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-unquantized 

Gemma 3 27B It Qat Q4 0 Unquantized Benchmarks

LMSys ELO 1366 vs 1272 (so35) 7.4%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 3 27B It Qat Q4 0 Unquantized Parameters and Internals

LLM NameGemma 3 27B It Qat Q4 0 Unquantized
Repository 🤗https://huggingface.co/google/gemma-3-27b-it-qat-q4_0-unquantized 
Base Model(s)  Gemma 3 27B It   google/gemma-3-27b-it
Model Size27b
Required VRAM55.3 GB
Updated2026-08-11
Maintainergoogle
Model Typegemma3
Model Files  4.8 GB: 1-of-12   5.0 GB: 2-of-12   5.0 GB: 3-of-12   5.0 GB: 4-of-12   5.0 GB: 5-of-12   5.0 GB: 6-of-12   5.0 GB: 7-of-12   5.0 GB: 8-of-12   5.0 GB: 9-of-12   5.0 GB: 10-of-12   5.0 GB: 11-of-12   0.5 GB: 12-of-12
Quantization Typeq4|q4_0
Model ArchitectureGemma3ForConditionalGeneration
Licensegemma
Transformers Version4.52.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Torch Data Typebfloat16

Quantized Models of the Gemma 3 27B It Qat Q4 0 Unquantized

Model
Likes
Downloads
VRAM
Gemma 3 27B It Qat32455 GB
Gemma 3 27B It Qat GGUF3033070 GB
Gemma 3 27B It Qat Abliterated2023108 GB
Amoral Gemma3 27B V2 Qat21955 GB
... 3 27B It Qat Unsloth Bnb 4bit31820 GB
Gemma 3 27B It Qat Bnb 4bit21616 GB

Best Alternatives to Gemma 3 27B It Qat Q4 0 Unquantized

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
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
Gemma 3 27B It 8bit0K / 31.2 GB4077
Note: green Score (e.g. "73.2") means that the model is better than google/gemma-3-27b-it-qat-q4_0-unquantized.