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.

ModelParametersNative VRAMFP8 VRAMINT4 VRAMLive GPU fit (native)Est. $/hrKV cache at 32K
canary-1b-v2979M4.4 GB1.1 GB0.5 GBRTX 3070$0.088/hrnot published for this architecture
canary-qwen-2.5b2.6B5.7 GB2.9 GB1.4 GBRTX 3070$0.088/hrnot 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)

ModelParametersPublished asVRAM neededLive GPU fitEst. $/hr
canary-1b-v2979MF324.4 GBRTX 3070$0.088/hr
canary-qwen-2.5b2.6BBF165.7 GBRTX 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

Start ComfyUI on a rented GPU.

© 2026 Aquanode. All rights reserved.

All trademarks, logos and brand names are the property of their respective owners.