SAVRN
Search Contact SAVRN

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.

Parameters965M
Context
Weights3.9 GB
License
AccessOpen weights
Monthly Downloads

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.

PrecisionWeightsMemory neededCheapest setupPer hourAlso 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.

Weights2 files · 3.9 GB
Configuration4 files · 2.8 KB
Tokenizer2 files · 1.5 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights3.9 GB c1165853d634
training_args.binWeights5.8 KB 2ea5013ba694
added_tokens.jsonConfiguration30 B
config.jsonConfiguration2.0 KB
preprocessor_config.jsonConfiguration254 B
special_tokens_map.jsonConfiguration548 B
.gitattributesRepository1.5 KB
tokenizer_config.jsonTokenizer1.1 KB
vocab.jsonTokenizer393 B

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
3.9 GB
Download from Claytone Sikasote

Released by Claytone Sikasote through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published3.9 GB
16-bit1.9 GB
8-bit1.0 GB
4-bit0.5 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.