bhili-tts
bhili-tts is an open-weight text to speech model from AI4Bharat with 938M 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
- AI4Bharat
- Released
- 21 May 2026
- Parameters
- 938M
- Type
- Text to speech
- License
- MIT
- HF downloads, 30 days
- 288
- Repository
- ai4bharat/bhili-tts
More from AI4Bharat
View allWill it run on your hardware?
How we estimate| Estimate or device | Memory |
|---|---|
| Q4 | 0.7 GB |
| Q8 | 1.2 GB |
| BF16 | 2.2 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) | ≈ 2.2 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 bhili-tts need? About 0.7 GB at 4-bit, 1.2 GB at 8-bit and 2.2 GB at 16-bit (BF16), for the weights plus runtime overhead.
Can I run bhili-tts 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 2.2 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
MIT. This license permits commercial use, modification and redistribution, as long as the copyright and license notice are kept. 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.