miracle-3 is an open-weight model from Amarsesin. It has 781M parameters. At 16-bit it needs about 1.9 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 miracle-3 (781M 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 | 1.6 GB | 1.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.4 GB | 0.5 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.
miracle-3 on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Identity and Version
- Repository
- Tok331102/miracle-3
- Publisher
- Amarsesin
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 781M parameters
- Languages
- Not stated by the source
- Revision
- 096747bdbcd825947795fb668a4e6547647896f6
- First published
- 2026-10-14
- Last updated
- 2026-10-14
Files and Weights
2 files, 3.1 GB in total. The weights are 1 file totalling 3.1 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.1 GB | b3d7272cd9bd |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.1 GB
Released by Amarsesin through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.1 GB |
| 16-bit | 1.6 GB |
| 8-bit | 0.8 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About miracle-3
How much GPU memory does miracle-3 need?
About 1.9 GB at 16-bit and 0.5 GB at 4-bit: the weights (781M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run miracle-3 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.