What GPU do I need to run nvidia/canary-qwen-2.5b?
2.6B parameters, published in BF16. View on Hugging Face
Set up canary-qwen-2.5bcanary-qwen-2.5b is published by nvidia on Hugging Face, with 23,677 downloads and 457 likes to date. It's a unlisted-architecture model built for automatic-speech-recognition, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activations and allocator fragmentation. Speech models don't build the same growing KV-cache a text model does. Memory scales primarily with input audio length. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 4.8 GB | 5.7 GB | RTX 3060 | 1 | $0.110/hr |
| FP8 (quantized) | 2.4 GB | 2.9 GB | RTX 4000 SFF Ada | 1 | $0.198/hr |
| INT4 (quantized) | 1.2 GB | 1.4 GB | RTX 3060 | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run canary-qwen-2.5b at its published (BF16) precision: 1× RTX 3060, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
canary-qwen-2.5b: common questions
How much VRAM does canary-qwen-2.5b need?
5.7 GB at BF16, 2.9 GB at FP8 (quantized), 1.4 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 4.8 GB of weights plus inference overhead is the whole requirement.
How many copies of canary-qwen-2.5b fit on one RTX 3060?
2, by VRAM alone. That card carries 12.0 GB and one copy needs 5.7 GB at BF16, on a live rate of $0.110/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Canary models
- canary-1b-v2 (979M, F32)
Alternatives at this size
Other models for automatic-speech-recognition within about a third of canary-qwen-2.5b's 2.6B parameters, from other model lines.
- Qwen3-ASR-1.7B (2.3B, BF16)
- cohere-transcribe-03-2026 (2.1B, BF16)
- seamless-m4t-v2-large (2.3B, F32)
- granite-speech-4.1-2b (2.3B, BF16)
- GLM-ASR-Nano-2512 (2.3B, BF16)
More on canary-qwen-2.5b
Fits on an 8 GB GPU at BF16: every model that fits in 8 GB.
Best speech-to-text models: how canary-qwen-2.5b ranks against the rest.
Related reading: H100 pricing and specs, Whisper variants compared, and What AI inference is.
