Includes Unsloth chat template fixes!
For llama.cpp, use --jinja

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

Safetensors

Model size

31B params

Tensor type

BF16

F8_E4M3

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for unsloth/Qwen3-30B-A3B-Thinking-2507-FP8

Base model

Quantized

Quantized

(1)

this model