kokoro-82m-safetensors is an open-weight model from Saidev Dhal. It has 82M parameters. At 16-bit it needs about 0.2 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 9 downloads a month.
Runs On
What it takes to serve kokoro-82m-safetensors (82M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.2 GB | 0.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Oct 18, 2026.
kokoro-82m-safetensors on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- sai1974dev/kokoro-82m-safetensors
- Publisher
- Saidev Dhal
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 82M parameters
- Languages
- Not stated by the source
- Revision
- 072e5d2a513e27e33de45ef5ac06be918b62c5b0
- First published
- 2026-06-03
- Last updated
- 2026-10-02
Files and Weights
9 files, 363.1 MB in total. The weights are 2 files totalling 355.3 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 327.1 MB | 4e9ecdf03b8b |
| voices.safetensors | Weights | 28.2 MB | eb5d6a54714a |
| config.json | Configuration | 2.4 KB | — |
| g2p/gb_gold.json.gz | Other | 723.9 KB | ca035bbf3072 |
| g2p/gb_silver.json.gz | Other | 2.4 MB | 9e749e20f947 |
| g2p/tagger_weights.json.gz | Other | 1.5 MB | 99085e4e421a |
| g2p/us_gold.json.gz | Other | 758.0 KB | d973775a9c22 |
| g2p/us_silver.json.gz | Other | 2.4 MB | ac40a524871b |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 355.3 MB
Released by Saidev Dhal through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 355.3 MB |
| 16-bit | 0.2 GB |
| 8-bit | 0.1 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About kokoro-82m-safetensors
How much GPU memory does kokoro-82m-safetensors need?
About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (82M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run kokoro-82m-safetensors on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.