Gemma 4 26B A4B QAT (4-bit)
Mixture-of-experts chat model from Google with text and image input.
Sourced directly from the model's publisher on huggingface.co. Please double-check links and verify before downloading.
- source https://huggingface.co/lmstudio-community/gemma-4-26B-A4B-it-QAT-MLX-4bit
- license apache-2.0
- base Gemma 4 26B A4B Instruct (QAT)
- published 2026-10-07 by MLX Community staff
> about this model
Gemma 4 26B A4B Instruct from Google, the quantization-aware-trained release, at 4-bit with the MLP and router layers at 8-bit. A mixture-of-experts model with 25.2B parameters in total and 3.8B active per token. Takes text and images.
> before you run it
Where did these weights come from?
The source link at the top of this page. Every catalog entry is published by a site admin and must carry a resolvable origin. There is no user upload path anywhere on this site.
Can I verify what I downloaded?
No checksum is published for this entry yet. Verify against the source repo's own file hashes before running it.
Will it fit in my memory?
Budget roughly 21 GB of unified memory. Context length and batch size push that up.
Is this hosted here?
No. We catalog and link; the bytes come from the origin repo. That keeps the chain of custody with whoever actually published the weights.