Skip to page content
SAVRN
Search Plan a project

Open-weight model

keural-alpha

by MKD Co., Ltd. mkd-dev/keural-alpha

keural-alpha is an open-weight model from MKD Co., Ltd.. It has 1B parameters. At 16-bit it needs about 2.4 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index.

Parameters1B
Context—
Weights—
License—
AccessOpen weights
Monthly Downloads—

Runs On

What it takes to serve keural-alpha (1B 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 2.0 GB 2.4 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 22, 2026.

keural-alpha on every accelerator the SAVRN Index prices, at every precision

Model Card

Identity and Version

Repository
mkd-dev/keural-alpha
Publisher
MKD Co., Ltd.
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
1B parameters
Languages
Not stated by the source
Revision
e69fc329fae80ab0b47b5ff9e973872e2d7a3a88
First published
2026-10-21
Last updated
2026-10-21

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download from MKD Co., Ltd.

Released by MKD Co., Ltd. through its official repository on Hugging Face.

Built From

  • Derived from mkd-ai/keural-alpha

Memory Requirements

PrecisionWeights in memory
16-bit2.0 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 keural-alpha

How much GPU memory does keural-alpha need?

About 2.4 GB at 16-bit and 0.6 GB at 4-bit: the weights (1B parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run keural-alpha 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.