MMS-Nahuatl-SOTA is an open-weight model from Bb. 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. It draws 8 downloads a month.
Runs On
What it takes to serve MMS-Nahuatl-SOTA (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 Oct 18, 2026.
MMS-Nahuatl-SOTA 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
- 40
- Stored precision
- float32
- Model type
- wav2vec2
Identity and Version
- Repository
- blaze1234567/MMS-Nahuatl-SOTA
- Publisher
- Bb
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 965M parameters
- Languages
- Not stated by the source
- Revision
- 2bc2a048694d952d23bcaf917ffa79451ac253a2
- First published
- 2026-09-24
- Last updated
- 2026-09-26
Files and Weights
18 files, 27.0 GB in total. The weights are 8 files totalling 27.0 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.9 GB | a9ecc75f7439 |
| training_args.bin | Weights | 5.6 KB | 38ea6a349e03 |
| version10.safetensors | Weights | 3.9 GB | 270083982275 |
| version11.safetensors | Weights | 3.9 GB | a9ecc75f7439 |
| version6.safetensors | Weights | 3.9 GB | 837586edf8f1 |
| version7.safetensors | Weights | 3.9 GB | ec070e0e7d88 |
| version8.safetensors | Weights | 3.9 GB | 74360179f6f3 |
| version9.safetensors | Weights | 3.9 GB | 498172dbe784 |
| config.json | Configuration | 2.1 KB | — |
| optimal_params.json | Configuration | 88 B | — |
| preprocessor_config.json | Configuration | 254 B | — |
| special_tokens_map.json | Configuration | 544 B | — |
| nahuatl_lm.arpa | Other | 2.3 MB | 2774e4be110e |
| nahuatl_lm.binary | Other | 878.4 KB | 5ba18b40ce8f |
| unigrams.txt | Other | 159.6 KB | — |
| .gitattributes | Repository | 1.6 KB | — |
| tokenizer_config.json | Tokenizer | 1.1 KB | — |
| vocab.json | Tokenizer | 966.3 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 27.0 GB
Released by Bb through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 27.0 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-Nahuatl-SOTA
How much GPU memory does MMS-Nahuatl-SOTA 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-Nahuatl-SOTA 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.