Canary models
2 Canary models on Hugging Face, from 979M to 2.6B parameters. At the precision each one is published in, the smallest needs about 4.4 GB of VRAM (canary-1b-v2, cheapest live fit: V100) and the largest about 5.7 GB (canary-qwen-2.5b, cheapest live fit: RTX 3060). The cheapest way to run canary-1b-v2 is $0.088/hr.
Canary models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| canary-1b-v2 | 979M | F32 | 4.4 GB | V100 | $0.088/hr |
| canary-qwen-2.5b | 2.6B | BF16 | 5.7 GB | RTX 3060 | $0.110/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from NVIDIA
- Parakeet (7 models)
- Nemotron 3 (16 models)
- Cosmos (6 models)
- Nemotron Nano (4 models)
- Nemotron (5 models)
- Nemotron Labs (4 models)
- Nemotron-H (3 models)
