Open-weight model
mms-1b-all-nyagen-combined-ft-62
by Claytone Sikasote csikasote/mms-1b-all-nyagen-combined-ft-62
mms-1b-all-nyagen-combined-ft-62 is an open-weight model from Claytone Sikasote. It has 965M parameters. At 16-bit it needs about 2.3 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 mms-1b-all-nyagen-combined-ft-62 (965M 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 | 1.9 GB | 2.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 1.0 GB | 1.2 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.5 GB | 0.6 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 Sep 20, 2026.
mms-1b-all-nyagen-combined-ft-62 on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Wav2Vec2ForCTC
- Layers
- 48
- Hidden size
- 1,280
- Feed-forward size
- 5,120
- Attention heads
- 16
- Vocabulary size
- 31
- Stored precision
- float32
- Model type
- wav2vec2
Identity and Version
- Repository
- csikasote/mms-1b-all-nyagen-combined-ft-62
- Publisher
- Claytone Sikasote
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 965M parameters
- Languages
- Not stated by the source
- Revision
- 59e4a07cf0b3d80db52e3f77dbff0d8528f9baba
- First published
- 2026-09-19
- Last updated
- 2026-09-19
Files and Weights
9 files, 3.9 GB in total. The weights are 2 files totalling 3.9 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.9 GB | c1165853d634 |
| training_args.bin | Weights | 5.8 KB | 2ea5013ba694 |
| added_tokens.json | Configuration | 30 B | — |
| config.json | Configuration | 2.0 KB | — |
| preprocessor_config.json | Configuration | 254 B | — |
| special_tokens_map.json | Configuration | 548 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
| vocab.json | Tokenizer | 393 B | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.9 GB
Released by Claytone Sikasote through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.9 GB |
| 16-bit | 1.9 GB |
| 8-bit | 1.0 GB |
| 4-bit | 0.5 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About mms-1b-all-nyagen-combined-ft-62
How much GPU memory does mms-1b-all-nyagen-combined-ft-62 need?
About 2.3 GB at 16-bit and 0.6 GB at 4-bit: the weights (965M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run mms-1b-all-nyagen-combined-ft-62 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.