LLM EXPLORER 65,548 MODELS INDEXED

Gemma 4 31B It AWQ by QuantTrio

By QuantTrio · 451491 downloads
HF Repo ↗ Copy URL

Gemma 4 31B It AWQ is an open-source language model by QuantTrio. Features: 31b LLM, VRAM: 20.6GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.48, ELO: 1451.

  4-bit   Awq Base model:google/gemma-4-31b-... Base model:quantized:google/ge...   Conversational   Endpoints compatible   Gemma4   Image-text-to-text   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/QuantTrio/gemma-4-31B-it-AWQ 

Gemma 4 31B It AWQ Benchmarks

LMSys ELO 1451 vs 1272 (so35) 14.1%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Gemma 4 31B It AWQ Parameters and Internals

LLM NameGemma 4 31B It AWQ
Repository 🤗https://huggingface.co/QuantTrio/gemma-4-31B-it-AWQ 
Base Model(s)  Gemma 4 31B It   google/gemma-4-31B-it
Model Size31b
Required VRAM20.6 GB
Updated2026-10-25
MaintainerQuantTrio
Model Typegemma4
Model Files  2.8 GB: 1-of-7   3.0 GB: 2-of-7   3.0 GB: 3-of-7   3.0 GB: 4-of-7   3.0 GB: 5-of-7   3.0 GB: 6-of-7   2.8 GB: 7-of-7
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B It AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 31B It AWQ 4bit0K / 20.9 GB26535151
Gemma 4 31B It AWQ 4bit0K / 20.9 GB381
Gemma 4 31B It AWQ 8bit0K / 35.1 GB361
Gemma 4 31B It Qat AWQ INT40K / 20.9 GB3138177
Gemma 4 31B AWQ 4bit0K / 20.9 GB361
Gemma 4 31B AWQ 8bit0K / 35.1 GB281
Gemma 4 31B It 4bit0K / 18.5 GB4506746
...emma 4 31B It Unsloth Bnb 4bit0K / 19.2 GB2075025
... 4 31B It Qat Q4 0 Unquantized0K / 62.6 GB997239
... 4 31B It Qat Q4 0 Unquantized0K / 62.6 GB20744