metadata
tags:
- uqff
- mistral.rs
base_model: HuggingFaceTB/SmolLM3-3B
base_model_relation: quantized
HuggingFaceTB/SmolLM3-3B, UQFF quantization
Run with mistral.rs. Documentation: UQFF docs.
- Flexible 🌀: Multiple quantization formats in one file format with one framework to run them all.
- Reliable 🔒: Compatibility ensured with embedded and checked semantic versioning information from day 1.
- Easy 🤗: Download UQFF models easily and quickly from Hugging Face, or use a local file.
- Customizable 🛠️: Make and publish your own UQFF files in minutes.
Examples
| Quantization type(s) | Example |
|---|---|
| AFQ4 | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-afq4-0.uqff |
| AFQ6 | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-afq6-0.uqff |
| AFQ8 | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-afq8-0.uqff |
| F8E4M3 | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-f8e4m3-0.uqff |
| Q4K | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-q4k-0.uqff |
| Q5K | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-q5k-0.uqff |
| Q8_0 | ./mistralrs-server -i plain -m EricB/SmolLM3-3B-UQFF -f smollm33b-q8_0-0.uqff |