Gemma4-26B-MoE-Q4

mavis-ai/Gemma4-26B-MoE-Q4

Image Text to Text4.6B parametersmlxLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
383
Total downloads
3,406
Gained 7D
Gained 30D
Likes
2
Rank · tracked models
#29,594
337(down 337 places)this week
Parameters
4.6B
Last source update
Jul 1, 2026
  • It moved from #2842 to #2883 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Gemma4-26B-MoE-Q4 is a image text to text model published by mavis-ai. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 1h ago.

Published
Apr 24, 2026
Last updated
Jul 1, 2026
Library
mlx
License
apache-2.0
Task
Image Text to Text
Parameters
4,571,325,006
Spaces
Derivative models
Velocity 7D/day
mlxsafetensorsgemma4image-text-to-textconversationalbase_model:google/gemma-4-26B-A4Bbase_model:quantized:google/gemma-4-26B-A4Blicense:apache-2.04-bitregion:us

Publisher

mavis-aiView publisher statistics →

Derived from google/gemma-4-26B-A4B (reported by the source; parent not yet tracked).

Similar models

Models similar to Gemma4-26B-MoE-Q4
ModelDL 30D
gemma-4-26B-A4B-it-QAT-MLX-4bitlmstudio-community562.6K
gemma-4-26B-A4B-it-MLX-4bitlmstudio-community166.5K
gemma-4-26B-A4B-it-qat-4bitmlx-community2,573
gemma-4-26B-A4B-it-heretic-4bitmlx-community2,336
supergemma4-26b-abliterated-multimodal-mlx-4bitJiunsong1,919
Qwen3.5-4B-quantized.w4a16RedHatAI14.9K