tasks · tinymodels.co
Tiny text-generation models
Every text-generation model in the catalogue, with the size and licence stated and one measured millisecond figure per model — one fixed input, one machine, one method.
Browse by format instead: gguf, mlx, safetensors.
| model | params | size | licence | one fixed input (ms) | |
|---|---|---|---|---|---|
| Qwen3-0.6B | 752M | 1.50 GB | apache-2.0 | 469.6 | Get |
| SmolLM2-135M-Instruct | 135M | 269 MB | apache-2.0 | 110.2 | Get |
| Qwen2.5-0.5B-Instruct-4bit | 494M | 278 MB | apache-2.0 | 241.4 | Get |
| Qwen2.5-0.5B-Instruct-GGUF | 494M | 491 MB | apache-2.0 | 255.4 | Get |
| Qwen2.5-0.5B-Instruct | 494M | 988 MB | apache-2.0 | 266.8 | Get |
The millisecond figure is one fixed input per task type, measured on this hub's machine with one warm-up run then one timed run. How these numbers were taken; the whole run, every model, is the measured bench dataset.