Hugging Face's logo

tikeape
/
qwen3-4B-Instruct-2507-minimax-m2-distill

GGUF
qwen3
llama.cpp
unsloth
conversational
Model card Files
xet
Community

qwen3-4B-Instruct-2507-minimax-m2-distill

This model was finetuned and converted to GGUF format using Unsloth.

This model was trained on 250 sample of MiniMax-M2 but excluded the thinking to achieve faster response times. It is not a replacement for the full model but merely aims to capture it style in a smaller model.

Downloads last month
520
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to view the estimation

4-bit

5-bit

8-bit

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

Collection including tikeape/qwen3-4B-Instruct-2507-minimax-m2-distill