My own (ZeroWw) quantizations. output and embed tensors quantized to f16. all other tensors quantized to q5_k or q6_k.

Result: both f16.q6 and f16.q5 are smaller than q8_0 standard quantization and they perform as well as the pure f16.

Updated on: Tue Apr 29, 06:15:00

GGUF

Model size

4.02B params

Architecture

qwen3

Hardware compatibility

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

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

Collection including ZeroWw/Qwen3-4B-GGUF