RMBG-2.0 is an open-weight model from Noer Holis. It has 221M parameters. At 16-bit it needs about 0.5 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 RMBG-2.0 (221M 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 | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.2 GB | 0.3 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.1 GB | 0.1 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.
RMBG-2.0 on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- BiRefNet
Identity and Version
- Repository
- NoerC/RMBG-2.0
- Publisher
- Noer Holis
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 221M parameters
- Languages
- Not stated by the source
- Revision
- 352229820c94ffa4b45ec30fc6c5d8f1f5778d80
- First published
- 2026-10-07
- Last updated
- 2026-10-07
Files and Weights
18 files, 5.4 GB in total. The weights are 10 files totalling 5.4 GB in bin, onnx, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 884.9 MB | 566ed80c3d95 |
| onnx/model.onnx | Weights | 1.0 GB | 5b486f08200f |
| onnx/model_bnb4.onnx | Weights | 355.3 MB | dadc9222fbff |
| onnx/model_fp16.onnx | Weights | 513.6 MB | 9dc47db40d11 |
| onnx/model_int8.onnx | Weights | 366.1 MB | f8ee7690d8c5 |
| onnx/model_q4.onnx | Weights | 367.5 MB | a813e0eab56c |
| onnx/model_q4f16.onnx | Weights | 233.8 MB | 8bfeb5f93220 |
| onnx/model_quantized.onnx | Weights | 366.1 MB | fcea23951a37 |
| onnx/model_uint8.onnx | Weights | 366.1 MB | fcea23951a37 |
| pytorch_model.bin | Weights | 885.1 MB | 0986c2881028 |
| BiRefNet_config.py | Configuration | 298 B | — |
| birefnet.py | Configuration | 91.4 KB | — |
| config.json | Configuration | 405 B | — |
| preprocessor_config.json | Configuration | 391 B | — |
| collage5.png | Other | 4.5 MB | f9f802564aa1 |
| diagram1.png | Other | 21.3 KB | — |
| t4.png | Other | 2.2 MB | 43a9453f567d |
| .gitattributes | Repository | 1.8 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 5.4 GB
Released by Noer Holis through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 5.4 GB |
| 16-bit | 0.4 GB |
| 8-bit | 0.2 GB |
| 4-bit | 0.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About RMBG-2.0
How much GPU memory does RMBG-2.0 need?
About 0.5 GB at 16-bit and 0.1 GB at 4-bit: the weights (221M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run RMBG-2.0 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.