AI BriefingUnsloth releases Gemma 4 GGUF weights
·2026.06.06 00:02
Key point
Unsloth has released **MTP GGUF weights** for the 31B, 26B-A4B, and 12B models of Gemma 4.
Details
Unsloth has uploaded MTP GGUF weights for the Gemma 4 models to Hugging Face.
The supported models and formats are as follows:
- Target models: 31B, 26B-A4B, 12B
- Quantization formats: Q8, F16, BF16
With this update, developers can now infer and utilize Gemma 4 models more efficiently across various environments.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.