gc-sg-vlm-v1 is an open-weight model from Kaito Furuo. It has 860M parameters. At 16-bit it needs about 2.1 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 gc-sg-vlm-v1 (860M 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 | 1.7 GB | 2.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.9 GB | 1.0 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.
gc-sg-vlm-v1 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
- Kaito-F/gc-sg-vlm-v1
- Publisher
- Kaito Furuo
- Task
- Not stated by the source
- Modality
- Other
- Library
- diffusers
- Parameters
- 860M parameters
- Languages
- Not stated by the source
- Revision
- 22844860268653699a0a5de540068378c9182467
- First published
- 2026-10-15
- Last updated
- 2026-10-16
Files and Weights
42 files, 8.7 GB in total. The weights are 10 files totalling 8.7 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ckpt-10000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 7f922c25fee8 |
| ckpt-10000/vlm_connector.safetensors | Weights | 17.8 MB | e2e556b18b4b |
| ckpt-15000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | ff82712c1b7a |
| ckpt-15000/vlm_connector.safetensors | Weights | 17.8 MB | 871a99f3a64c |
| ckpt-20000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 0648c065ea0d |
| ckpt-20000/vlm_connector.safetensors | Weights | 17.8 MB | 911e7e92d808 |
| ckpt-5000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | f26375a732aa |
| ckpt-5000/vlm_connector.safetensors | Weights | 17.8 MB | 399f8261fa93 |
| unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 0648c065ea0d |
| vlm_connector.safetensors | Weights | 17.8 MB | 911e7e92d808 |
| ckpt-10000/sg_config.json | Configuration | 411 B | — |
| ckpt-10000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-15000/sg_config.json | Configuration | 411 B | — |
| ckpt-15000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-20000/sg_config.json | Configuration | 411 B | — |
| ckpt-20000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-5000/sg_config.json | Configuration | 410 B | — |
| ckpt-5000/unet/config.json | Configuration | 1.8 KB | — |
| sg_config.json | Configuration | 411 B | — |
| unet/config.json | Configuration | 1.8 KB | — |
| val/step-000000.jpg | Other | 199.9 KB | 38734f5cb74e |
| val/step-001000.jpg | Other | 198.5 KB | 3a5d3c00fd36 |
| val/step-002000.jpg | Other | 197.6 KB | b3b2ea095b5a |
| val/step-003000.jpg | Other | 197.1 KB | 70536e3b8467 |
| val/step-004000.jpg | Other | 196.8 KB | 98223b061ab5 |
| val/step-005000.jpg | Other | 196.8 KB | 4c727d380e91 |
| val/step-006000.jpg | Other | 196.1 KB | 38bd2fc75f0f |
| val/step-007000.jpg | Other | 196.4 KB | 20690d6d132e |
| val/step-008000.jpg | Other | 196.5 KB | 9558a007273a |
| val/step-009000.jpg | Other | 196.7 KB | ca275f7620b1 |
| val/step-010000.jpg | Other | 196.7 KB | 37c25821a52b |
| val/step-011000.jpg | Other | 196.5 KB | d27d0e36bb9c |
| val/step-012000.jpg | Other | 196.6 KB | c457d7cc76ab |
| val/step-013000.jpg | Other | 196.5 KB | d8d7d8ff7d33 |
| val/step-014000.jpg | Other | 196.6 KB | 8eddc715db32 |
| val/step-015000.jpg | Other | 196.6 KB | 935cd1110ba2 |
| val/step-016000.jpg | Other | 196.0 KB | 607aa7d2f42c |
| val/step-017000.jpg | Other | 196.1 KB | 1948dd6324db |
| val/step-018000.jpg | Other | 196.0 KB | 6ab068d10eb1 |
| val/step-019000.jpg | Other | 196.1 KB | 0051512b6014 |
| val/step-020000.jpg | Other | 195.8 KB | bbf6501f7488 |
| .gitattributes | Repository | 2.7 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 8.7 GB
Released by Kaito Furuo through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 8.7 GB |
| 16-bit | 1.7 GB |
| 8-bit | 0.9 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gc-sg-vlm-v1
How much GPU memory does gc-sg-vlm-v1 need?
About 2.1 GB at 16-bit and 0.5 GB at 4-bit: the weights (860M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gc-sg-vlm-v1 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.