UQFF
Collection
UQFF models. Examples for each in the model card!
β’
37 items
β’
Updated
β’
18
Qwen/Qwen3-32B, UQFF quantization
Run with mistral.rs. Documentation: UQFF docs.
| Quantization type(s) | Example |
|---|---|
| AFQ2 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f qwen332b-afq2-0.uqff |
| AFQ3 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-afq3-0.uqff;qwen332b-afq3-1.uqff" |
| AFQ4 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-afq4-0.uqff;qwen332b-afq4-1.uqff" |
| AFQ6 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-afq6-0.uqff;qwen332b-afq6-1.uqff;qwen332b-afq6-2.uqff" |
| AFQ8 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-afq8-0.uqff;qwen332b-afq8-1.uqff;qwen332b-afq8-2.uqff;qwen332b-afq8-3.uqff" |
| F8E4M3 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-f8e4m3-0.uqff;qwen332b-f8e4m3-1.uqff;qwen332b-f8e4m3-2.uqff" |
| Q2K | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f qwen332b-q2k-0.uqff |
| Q3K | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-q3k-0.uqff;qwen332b-q3k-1.uqff" |
| Q4K | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-q4k-0.uqff;qwen332b-q4k-1.uqff" |
| Q5K | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-q5k-0.uqff;qwen332b-q5k-1.uqff;qwen332b-q5k-2.uqff" |
| Q8_0 | ./mistralrs-server -i plain -m EricB/Qwen3-32B-UQFF -f "qwen332b-q8_0-0.uqff;qwen332b-q8_0-1.uqff;qwen332b-q8_0-2.uqff;qwen332b-q8_0-3.uqff" |
Base model
Qwen/Qwen3-32B