gc_sg4_pi05 is an open-weight model from Kaito Furuo. It has 4.1B parameters. At 16-bit it needs about 9.9 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 gc_sg4_pi05 (4.1B 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 | 8.3 GB | 9.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 4.1 GB | 5.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 2.1 GB | 2.5 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_sg4_pi05 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_sg4_pi05
- Publisher
- Kaito Furuo
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 4.1B parameters
- Languages
- Not stated by the source
- Revision
- 57cf0f855f47536c9cd2183ed7c78d909c25900e
- First published
- 2026-10-14
- Last updated
- 2026-10-14
Files and Weights
79 files, 9.7 GB in total. The weights are 27 files totalling 9.7 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| adapters/005000/adapter_model.safetensors | Weights | 41.0 MB | a564faf944ec |
| adapters/005000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/005000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/010000/adapter_model.safetensors | Weights | 41.0 MB | dddc04351d42 |
| adapters/010000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/010000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/015000/adapter_model.safetensors | Weights | 41.0 MB | eecbb97f5978 |
| adapters/015000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/015000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/020000/adapter_model.safetensors | Weights | 41.0 MB | 4dded507e039 |
| adapters/020000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/020000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/025000/adapter_model.safetensors | Weights | 41.0 MB | ac38244ecd67 |
| adapters/025000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/025000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/030000/adapter_model.safetensors | Weights | 41.0 MB | 80399575382b |
| adapters/030000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/030000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/035000/adapter_model.safetensors | Weights | 41.0 MB | b388f7248b6d |
| adapters/035000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/035000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/040000/adapter_model.safetensors | Weights | 41.0 MB | da8323ae7e9d |
| adapters/040000/policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/040000/policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| model.safetensors | Weights | 9.4 GB | ac259a811667 |
| policy_postprocessor_step_0_unnormalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| policy_preprocessor_step_2_normalizer_processor.safetensors | Weights | 8.7 KB | d085a910160a |
| adapters/005000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/005000/config.json | Configuration | 2.6 KB | — |
| adapters/005000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/005000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/005000/train_config.json | Configuration | 7.9 KB | — |
| adapters/010000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/010000/config.json | Configuration | 2.6 KB | — |
| adapters/010000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/010000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/010000/train_config.json | Configuration | 7.9 KB | — |
| adapters/015000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/015000/config.json | Configuration | 2.6 KB | — |
| adapters/015000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/015000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/015000/train_config.json | Configuration | 7.9 KB | — |
| adapters/020000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/020000/config.json | Configuration | 2.6 KB | — |
| adapters/020000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/020000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/020000/train_config.json | Configuration | 7.9 KB | — |
| adapters/025000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/025000/config.json | Configuration | 2.6 KB | — |
| adapters/025000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/025000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/025000/train_config.json | Configuration | 7.9 KB | — |
| adapters/030000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/030000/config.json | Configuration | 2.6 KB | — |
| adapters/030000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/030000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/030000/train_config.json | Configuration | 7.9 KB | — |
| adapters/035000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/035000/config.json | Configuration | 2.6 KB | — |
| adapters/035000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/035000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/035000/train_config.json | Configuration | 7.9 KB | — |
| adapters/040000/adapter_config.json | Configuration | 1.4 KB | — |
| adapters/040000/config.json | Configuration | 2.6 KB | — |
| adapters/040000/policy_postprocessor.json | Configuration | 660 B | — |
| adapters/040000/policy_preprocessor.json | Configuration | 2.1 KB | — |
| adapters/040000/train_config.json | Configuration | 7.9 KB | — |
| config.json | Configuration | 2.1 KB | — |
| policy_postprocessor.json | Configuration | 660 B | — |
| policy_preprocessor.json | Configuration | 2.0 KB | — |
| adapters/005000/README.md | Documentation | 5.1 KB | — |
| adapters/010000/README.md | Documentation | 5.1 KB | — |
| adapters/015000/README.md | Documentation | 5.1 KB | — |
| adapters/020000/README.md | Documentation | 5.1 KB | — |
| adapters/025000/README.md | Documentation | 5.1 KB | — |
| adapters/030000/README.md | Documentation | 5.1 KB | — |
| adapters/035000/README.md | Documentation | 5.1 KB | — |
| adapters/040000/README.md | Documentation | 5.1 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 9.7 GB
Released by Kaito Furuo through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 9.7 GB |
| 16-bit | 8.3 GB |
| 8-bit | 4.1 GB |
| 4-bit | 2.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About gc_sg4_pi05
How much GPU memory does gc_sg4_pi05 need?
About 9.9 GB at 16-bit and 2.5 GB at 4-bit: the weights (4.1B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run gc_sg4_pi05 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.