canary-1b-v2
canary-1b-v2 is an open-weight speech to text model from NVIDIA with 979M parameters. At 4-bit it needs about 0.7 GB of memory, so the smallest current device that fits it is the Mac mini M6 (16GB).
Overview
Estimated memory for the weights at 4-bit (plus runtime overhead). Image, video and speech models also need working memory that depends on resolution or clip length.
Key information
- Lab
- NVIDIA
- Released
- 4 Aug 2025
- Parameters
- 979M
- Type
- Speech to text
- License
- CC BY 4.0
- HF downloads, 30 days
- 231,008
- Repository
- nvidia/canary-1b-v2
More from NVIDIA
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 0.7 GB |
| Q8 | 1.2 GB |
| BF16 | 2.3 GB |
| RTX 5060 Ti 16 GB | 16 GB usable |
| RTX 5090 32 GB | 32 GB usable |
| DGX Spark 128 GB | 108.8 GB usable |
| Mac Studio M5 Ultra 256 GB | 192 GB usable |
Single-device memory estimate. Pick a device to update the On your device column.
36 GB usable memory
| Format | Memory needed | On your device | Example hardware |
|---|---|---|---|
| 4-bit (Q4) | ≈ 0.7 GB | Fits 2% | Mac mini M6 (16GB)16 GB memory |
| 8-bit (Q8) | ≈ 1.2 GB | Fits 3% | Mac mini M6 (16GB)16 GB memory |
| 16-bit (BF16) | ≈ 2.3 GB | Fits 6% | Mac mini M6 (16GB)16 GB memory |
Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.
Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.
Where to run it
Through an API
No hosted API found.
More about this model
Frequently asked questions
How much memory does canary-1b-v2 need? About 0.7 GB at 4-bit, 1.2 GB at 8-bit and 2.3 GB at 16-bit (BF16), for the weights plus runtime overhead.
Can I run canary-1b-v2 on a Mac? The smallest current Mac that fits the 4-bit estimate of 0.7 GB is the Mac mini M6 (16GB). We have not found a trusted MLX or GGUF build yet.
What does it need to run? The weights need about 0.7 GB at 4-bit and 2.3 GB at 16-bit. Image, video and speech models also need working memory that depends on resolution or clip length, so leave extra room. We have not found a trusted MLX or GGUF build yet.
What does it cost through an API? We did not find a hosted API for this model.
License in plain English
CC BY 4.0. This license allows sharing and adapting, including for commercial use, as long as you give credit. This summary is not legal advice.
OMHQ RigBench
Not yet tested. We show no speed or quality score without a measurement.
Revision history and sources
Last updated . Sources:Hugging Face model card.