A2-4B-k1 is an open-weight model from Jiahao Jiang. It has 5.4B parameters. At 16-bit it needs about 13 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 A2-4B-k1 (5.4B 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 | 10.8 GB | 13.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 5.4 GB | 6.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.7 GB | 3.2 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 24, 2026.
A2-4B-k1 on every accelerator the SAVRN Index prices, at every precision
Model Card
Identity and Version
- Repository
- zaleni/A2-4B-k1
- Publisher
- Jiahao Jiang
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 5.4B parameters
- Languages
- Not stated by the source
- Revision
- 73511372bee6595a9b58268d7f3d99d089924c82
- First published
- 2026-10-23
- Last updated
- 2026-10-23
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
Released by Jiahao Jiang through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| 16-bit | 10.8 GB |
| 8-bit | 5.4 GB |
| 4-bit | 2.7 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About A2-4B-k1
How much GPU memory does A2-4B-k1 need?
About 13 GB at 16-bit and 3.2 GB at 4-bit: the weights (5.4B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run A2-4B-k1 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.