Unsloth Releases MTP GGUF Weights for Gemma 4, Supporting Multiple Quantized Sizes

Core summary

One sentence to understand this update

Unsloth has released MTP GGUF weights for Gemma 4 models, including Q8, F16, and BF16 quantized versions for 31B, 26B-A4B, and 12B scales.

Impact & opportunity

What this could mean

Local model developers can now more easily deploy and run optimized Gemma 4 models on various devices, improving efficiency and compatibility.