Vigyan-AI-32B is an open-weight model from Shreyansh singh, released under Creative Commons Attribution-NonCommercial 4.0. It has 32.2B parameters and a 4,096-token context. At 16-bit it needs about 77.4 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 70 downloads a month.
Runs On
What it takes to serve Vigyan-AI-32B (32.2B 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 | 64.5 GB | 77.4 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 32.2 GB | 38.7 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 16.1 GB | 19.3 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 7, 2026.
Vigyan-AI-32B on every accelerator the SAVRN Index prices, at every precision
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- Olmo2ForCausalLM
- Context length (tokens)
- 4,096
- Layers
- 64
- Hidden size
- 5,120
- Feed-forward size
- 27,648
- Attention heads
- 40
- Key/value heads
- 8
- Vocabulary size
- 100,352
- Model type
- olmo2
Identity and Version
- Repository
- shreyansh12183/Vigyan-AI-32B
- Publisher
- Shreyansh singh
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 32.2B parameters
- Languages
- Not stated by the source
- Revision
- de3ca32f1084d332f7810857306682e90f226143
- First published
- 2026-09-19
- Last updated
- 2026-10-06
Files and Weights
21 files, 64.5 GB in total. The weights are 14 files totalling 64.5 GB in safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model-00001-of-00014.safetensors | Weights | 5.0 GB | 6b236f4c7e5e |
| model-00002-of-00014.safetensors | Weights | 4.9 GB | 09f47b1fdd1d |
| model-00003-of-00014.safetensors | Weights | 4.9 GB | 81e736819c08 |
| model-00004-of-00014.safetensors | Weights | 4.9 GB | 6949ff05b470 |
| model-00005-of-00014.safetensors | Weights | 4.9 GB | 7d15f9fe2cd7 |
| model-00006-of-00014.safetensors | Weights | 4.9 GB | e37aa627b43d |
| model-00007-of-00014.safetensors | Weights | 4.9 GB | fea21c7f9057 |
| model-00008-of-00014.safetensors | Weights | 4.9 GB | ed921116487f |
| model-00009-of-00014.safetensors | Weights | 4.9 GB | 527c1ca06498 |
| model-00010-of-00014.safetensors | Weights | 4.9 GB | ac4539cf6002 |
| model-00011-of-00014.safetensors | Weights | 4.9 GB | 7ad67b5cc179 |
| model-00012-of-00014.safetensors | Weights | 4.9 GB | 9cb27e21b2c6 |
| model-00013-of-00014.safetensors | Weights | 4.9 GB | 2dfbdd1a0339 |
| model-00014-of-00014.safetensors | Weights | 975.2 MB | 17af375d5840 |
| config.json | Configuration | 677 B | — |
| generation_config.json | Configuration | 147 B | — |
| model.safetensors.index.json | Configuration | 59.1 KB | — |
| README.md | Documentation | 31 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 7.1 MB | — |
| tokenizer_config.json | Tokenizer | 369 B | — |
License and Download
- License
- cc-by-nc-4.0
- Access
- Open weights, no gate
- Download size
- 64.5 GB
Released by Shreyansh singh through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 64.5 GB |
| 16-bit | 64.5 GB |
| 8-bit | 32.2 GB |
| 4-bit | 16.1 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Vigyan-AI-32B
How much GPU memory does Vigyan-AI-32B need?
About 77.4 GB at 16-bit and 19.3 GB at 4-bit: the weights (32.2B parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run Vigyan-AI-32B 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.
Can I use Vigyan-AI-32B commercially?
Not without separate permission. Vigyan-AI-32B is released under Creative Commons Attribution-NonCommercial 4.0. CC BY-NC 4.0 permits sharing and adapting with credit for non-commercial purposes only. Commercial use needs separate permission from the rights holder.
What is Vigyan-AI-32B's context length?
4,096 tokens, from the maximum position embeddings in its published configuration.