LLM EXPLORER 59,598 MODELS INDEXED

Gemma 4 26B A4B It Qat AWQ INT4 by cyankiwi

By cyankiwi · 231431 downloads
HF Repo ↗ Copy URL

Gemma 4 26B A4B It Qat AWQ INT4 is an open-source language model by cyankiwi. Features: 26b LLM, VRAM: 17.2GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.35.

  Awq Base model:google/gemma-4-26b-... Base model:quantized:google/ge...   Compressed-tensors   Conversational   Endpoints compatible   Gemma4   Image-text-to-text   Q4   Q4 0   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/cyankiwi/gemma-4-26B-A4B-it-qat-AWQ-INT4 

Gemma 4 26B A4B It Qat AWQ INT4 Parameters and Internals

LLM NameGemma 4 26B A4B It Qat AWQ INT4
Repository 🤗https://huggingface.co/cyankiwi/gemma-4-26B-A4B-it-qat-AWQ-INT4 
Base Model(s)  ...6B A4B It Qat Q4 0 Unquantized   google/gemma-4-26B-A4B-it-qat-q4_0-unquantized
Model Size26b
Required VRAM17.2 GB
Updated2026-08-11
Maintainercyankiwi
Model Typegemma4
Model Files  17.2 GB
AWQ QuantizationYes
Quantization Typeawq|q4|q4_0
Model ArchitectureGemma4ForConditionalGeneration
Licenseapache-2.0
Transformers Version5.10.2
Tokenizer ClassGemmaTokenizer
Padding Token<pad>

Best Alternatives to Gemma 4 26B A4B It Qat AWQ INT4

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 4 26B A4B It AWQ 4bit0K / 17.3 GB306902391
...x Imatrix3plus AWQ High6 Top400K / 15.5 GB410
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB3369650
Gemma 4 26B A4b It 4bit0K / 15.4 GB2754379
...6B A4B It Qat Q4 0 Unquantized0K / 51.6 GB34873
Gemma 4 26B A4b It 8bit0K / 27.9 GB291714
Gemma 4 26B A4b It UD MLX 4bit0K / 16.2 GB152734
Gemma 4 26B A4b It MLX 8bit0K / 27.9 GB93616
...at Q4 0 Unquantized Heretic Ja0K / 51.6 GB341
Gemma 4 26B A4b 4bit0K / 15.6 GB48819
Note: green Score (e.g. "73.2") means that the model is better than cyankiwi/gemma-4-26B-A4B-it-qat-AWQ-INT4.