Qwen/Qwen3-4B, UQFF quantization

Run with mistral.rs. Documentation: UQFF docs.

  1. Flexible πŸŒ€: Multiple quantization formats in one file format with one framework to run them all.
  2. Reliable πŸ”’: Compatibility ensured with embedded and checked semantic versioning information from day 1.
  3. Easy πŸ€—: Download UQFF models easily and quickly from Hugging Face, or use a local file.
  4. Customizable πŸ› οΈ: Make and publish your own UQFF files in minutes.

Examples

Quantization type(s) Example
AFQ2 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-afq2-0.uqff
AFQ3 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-afq3-0.uqff
AFQ4 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-afq4-0.uqff
AFQ6 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-afq6-0.uqff
AFQ8 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-afq8-0.uqff
F8E4M3 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-f8e4m3-0.uqff
Q2K ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-q2k-0.uqff
Q3K ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-q3k-0.uqff
Q4K ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-q4k-0.uqff
Q5K ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-q5k-0.uqff
Q8_0 ./mistralrs-server -i plain -m EricB/Qwen3-4B-UQFF -f qwen34b-q8_0-0.uqff
Downloads last month
35
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for EricB/Qwen3-4B-UQFF

Base model

Qwen/Qwen3-4B-Base
Finetuned
Qwen/Qwen3-4B
Quantized
(96)
this model

Collection including EricB/Qwen3-4B-UQFF