LLM EXPLORER 64,442 MODELS INDEXED

Gemma 4 31B AWQ 8bit by axteam

By axteam · 28 downloads
HF Repo ↗ Copy URL

Gemma 4 31B AWQ 8bit is an open-source language model by axteam. Features: 31b LLM, VRAM: 35.1GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

  8bit   Awq   Base model:google/gemma-4-31b Base model:quantized:google/ge...   Compressed-tensors   Endpoints compatible   Gemma   Gemma4   Image-text-to-text   Int8   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Vllm
Model Card on HF 🤗: https://huggingface.co/axteam/gemma-4-31B-AWQ-8bit 

Gemma 4 31B AWQ 8bit Parameters and Internals

LLM NameGemma 4 31B AWQ 8bit
Repository 🤗https://huggingface.co/axteam/gemma-4-31B-AWQ-8bit 
Base Model(s)  Gemma 4 31B   google/gemma-4-31B
Model Size31b
Required VRAM35.1 GB
Updated2026-10-15
Maintaineraxteam
Model Typegemma4
Model Files  19.9 GB: 1-of-2   15.2 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq|8bit
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.5.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 31B AWQ 8bit

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 It 4bit0K / 18.5 GB4506746
... 4 31B It Qat Q4 0 Unquantized0K / 62.6 GB997239
...emma 4 31B It Unsloth Bnb 4bit0K / 19.2 GB1970625
... 4 31B It Qat Q4 0 Unquantized0K / 62.6 GB20744
Gemma 4 31B It 8bit0K / 33.8 GB321417
Note: green Score (e.g. "73.2") means that the model is better than axteam/gemma-4-31B-AWQ-8bit.