gc-sg-ip2p-v6pt3 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-ip2p-v6pt3 (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-ip2p-v6pt3 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-ip2p-v6pt3
- Publisher
- Kaito Furuo
- Task
- Not stated by the source
- Modality
- Other
- Library
- diffusers
- Parameters
- 860M parameters
- Languages
- Not stated by the source
- Revision
- 31943a7503c11ed24ddab84930203669df51c626
- First published
- 2026-10-18
- Last updated
- 2026-10-18
Files and Weights
41 files, 10.3 GB in total. The weights are 6 files totalling 10.3 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| ckpt-10000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 450d0d40ca08 |
| ckpt-2000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 755ad3d2ac25 |
| ckpt-4000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | a94a5522aa94 |
| ckpt-6000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 8adea0b861b2 |
| ckpt-8000/unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 8b6824f9e92e |
| unet/diffusion_pytorch_model.safetensors | Weights | 1.7 GB | 450d0d40ca08 |
| ckpt-10000/sg_config.json | Configuration | 363 B | — |
| ckpt-10000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-2000/sg_config.json | Configuration | 362 B | — |
| ckpt-2000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-4000/sg_config.json | Configuration | 362 B | — |
| ckpt-4000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-6000/sg_config.json | Configuration | 362 B | — |
| ckpt-6000/unet/config.json | Configuration | 1.8 KB | — |
| ckpt-8000/sg_config.json | Configuration | 362 B | — |
| ckpt-8000/unet/config.json | Configuration | 1.8 KB | — |
| sg_config.json | Configuration | 363 B | — |
| stage2/holdout_v6pt3.json | Configuration | 62.7 KB | — |
| unet/config.json | Configuration | 1.8 KB | — |
| stage2/holdout_v6pt3.jpg | Other | 3.8 MB | b96f22a73593 |
| thumbs/thumbs_libero_goal10_init0.jpg | Other | 251.2 KB | 26f8f61f2d63 |
| thumbs/thumbs_libero_rlgen_init0_p00.jpg | Other | 529.2 KB | 245797ade307 |
| thumbs/thumbs_libero_rlgen_init0_p01.jpg | Other | 514.1 KB | 3ea12431adff |
| thumbs/thumbs_libero_rlgen_init0_p02.jpg | Other | 554.1 KB | a4e69de113da |
| thumbs/thumbs_libero_rlgen_init0_p03.jpg | Other | 430.9 KB | 8e018273f3b4 |
| thumbs/thumbs_libero_t3gen_init0_p00.jpg | Other | 553.4 KB | 44b2dc4c5631 |
| thumbs/thumbs_libero_t3gen_init0_p01.jpg | Other | 556.1 KB | dd8677806a18 |
| thumbs/thumbs_libero_t3gen_init0_p02.jpg | Other | 519.7 KB | 51c491db7279 |
| thumbs/thumbs_libero_t3gen_init0_p03.jpg | Other | 456.6 KB | 45c45ee04756 |
| val/step-000000.jpg | Other | 208.4 KB | bbb0fa94b313 |
| val/step-001000.jpg | Other | 209.1 KB | 45d5bc5fc4ca |
| val/step-002000.jpg | Other | 208.8 KB | ead9ed3a49e9 |
| val/step-003000.jpg | Other | 208.8 KB | 441e7c91113f |
| val/step-004000.jpg | Other | 208.8 KB | 04d890c5f4a9 |
| val/step-005000.jpg | Other | 208.7 KB | d15a873cfb8e |
| val/step-006000.jpg | Other | 208.6 KB | 928d4322ac6f |
| val/step-007000.jpg | Other | 208.9 KB | fdc6d3684e6b |
| val/step-008000.jpg | Other | 208.7 KB | 923180cb0e4f |
| val/step-009000.jpg | Other | 208.6 KB | 8fdc8bed9c35 |
| val/step-010000.jpg | Other | 208.5 KB | 225810aa7740 |
| .gitattributes | Repository | 2.9 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 10.3 GB
Released by Kaito Furuo through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 10.3 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-ip2p-v6pt3
How much GPU memory does gc-sg-ip2p-v6pt3 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-ip2p-v6pt3 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.