kastom is an open-weight model from Nabad. It has 28M parameters. At 16-bit it needs about 0.1 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.
Runs On
What it takes to serve kastom (28M 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 | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 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 19, 2026.
kastom on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- KokoTTSModel
- Vocabulary size
- 120
- Model type
- koko-tts
Identity and Version
- Repository
- hoskasii/kastom
- Publisher
- Nabad
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 28M parameters
- Languages
- Not stated by the source
- Revision
- ed89cfd59aab631dd7e2da621cd6a98fa9c597d0
- First published
- 2026-10-15
- Last updated
- 2026-10-16
Files and Weights
9 files, 113.9 MB in total. The weights are 1 file totalling 113.8 MB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 113.8 MB | 2ff4f1d8a631 |
| config.json | Configuration | 566 B | — |
| modeling_koko_tts.py | Configuration | 22.6 KB | — |
| processing_koko_tts.py | Configuration | 3.4 KB | — |
| processor_config.json | Configuration | 124 B | — |
| __pycache__/modeling_koko_tts.cpython-313.pyc | Other | 37.8 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.5 KB | — |
| tokenizer_config.json | Tokenizer | 318 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 113.8 MB
Released by Nabad through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 113.8 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About kastom
How much GPU memory does kastom need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (28M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run kastom 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.