Canary models
2 Canary models from NVIDIA on Hugging Face, from 979M to 2.6B parameters, published by NVIDIA in F32 and BF16, with a 1K-token context. The smallest official model, canary-1b-v2, needs about 4.4 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Pick a size
One row per official Canary size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| canary-1b-v2 | 979M | 4.4 GB | 1.1 GB | 0.5 GB | RTX 3070 | $0.088/hr | not published for this architecture |
| canary-qwen-2.5b | 2.6B | 5.7 GB | 2.9 GB | 1.4 GB | RTX 3070 | $0.088/hr | not published for this architecture |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| canary-1b-v2 | 979M | F32 | 4.4 GB | RTX 3070 | $0.088/hr |
| canary-qwen-2.5b | 2.6B | BF16 | 5.7 GB | RTX 3070 | $0.088/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. 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 (8 models)
- Nemotron 3 (19 models)
- Cosmos (7 models)
- Nemotron Nano (6 models)
- nvidia (2 models)
- Nemotron Labs (5 models)
- Nemotron Speech (1 models)
- Nemotron Parse (1 models)
- Nemotron-H (3 models)
- Nemotron Cascade (1 models)
- Nemotron VoiceChat (1 models)