sarvam 30b GGUF IQ2 M IQ1 M needs about 8.6 GB of memory at IQ1_M (a 7.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 7.9 GB (IQ1_M) to 11.0 GB (IQ2_M). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.
32.2B‑parameter Mixture‑of‑Experts model for reasoning and tool use
Sarvam‑30B is a 32.2‑billion‑parameter Mixture‑of‑Experts model built on the bailingmoe2 architecture. It is optimized for throughput and memory efficiency, with 19 layers and 128 experts. The model is open‑source under Apache‑2.0 and supports reasoning and tool calling.
Good at
- Reasoning
- Tool calling
- Multilingual Indian language support
Limits
- Requires 8‑k context for memory estimates
- No vision support
- Large model size limits low‑VRAM use
Best for
- Deploying reasoning agents on CPUs
- Building multilingual chatbots
- Running tool‑enabled workflows
Who it’s for. Developers who need a high‑capacity reasoning model that can run on commodity CPUs with sufficient RAM. The model is suitable for applications requiring Indian‑language understanding and tool integration.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 7.9 GB | 8.6 GB | Too big | Get file → | |
| IQ2_M | 11.0 GB | 11.7 GB | Too big | Get file → |
For 8‑GB RAM, use the IQ1_M quant (7.9 GB file, 8.6 GB memory at 8‑k context). For 12‑GB RAM, use IQ2_M (11.05 GB file, 11.7 GB memory at 8‑k context). Memory estimates are approximate.
What GPU do you need for sarvam 30b GGUF IQ2 M IQ1 M?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_M (11.0 GB file, about 11.7 GB in use).
Which sarvam 30b GGUF IQ2 M IQ1 M quant should you choose?
IQ1_M (7.9 GB) is the middle option in this repository. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about sarvam 30b GGUF IQ2 M IQ1 M
How much VRAM does sarvam 30b GGUF IQ2 M IQ1 M need?
About 8.6 GB at IQ1_M with an 8K context window. That is the 7.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run sarvam 30b GGUF IQ2 M IQ1 M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of sarvam 30b GGUF IQ2 M IQ1 M GGUF?
It depends on the quant: IQ1_M is 7.9 GB, IQ2_M is 11.0 GB.
What context length does sarvam 30b GGUF IQ2 M IQ1 M support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.
Where can I download sarvam 30b GGUF IQ2 M IQ1 M GGUF?
The files are on Hugging Face in the Aaravomega/sarvam-30b-GGUF-IQ2_M-IQ1_M repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does sarvam 30b GGUF IQ2 M IQ1 M use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Sarvam‑30B on a CPU with 12 GB of free RAM?
Yes, the IQ2_M quant requires about 11.7 GB of RAM at 8‑k context, which fits a 12 GB free‑RAM CPU setup.
Does Sarvam‑30B support vision tasks?
No, the model has no vision support; it is text‑only.
What license applies to Sarvam‑30B?
The model is released under the Apache‑2.0 license.