Sarvam 30b Uncensored needs about 20.2 GB of memory at Q4_K_M (a 19.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 24 quants, from 0.1 GB to 26.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.
Sarvam 30b Uncensored – 32.2B parameter Mixture‑of‑Experts model
Sarvam 30b Uncensored is a 32.2B parameter Mixture‑of‑Experts model based on the Sarvam family. It retains full reasoning, multilingual, coding, and agentic capabilities while removing refusal and alignment mechanisms. The model supports a 131072 token context window.
Good at
- Reasoning across complex prompts
- Multilingual support in Indian languages
- Tool‑using agentic tasks
Limits
- No vision or audio input
- Requires 131072 token context for full capability
- Apache‑2.0 license restricts commercial redistribution
Best for
- Research on large‑scale reasoning models
- Developing agentic applications
- Testing multilingual LLM behavior
Who it’s for. Researchers and developers who need a large Mixture‑of‑Experts model with full reasoning and multilingual abilities, and who are comfortable handling a 131072 token context window. The model is suitable for academic projects and internal tooling where alignment constraints are not required.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.7 GB | Fits | Get file → | |
| IQ1_S | 7.2 GB | 7.9 GB | Tight | Get file → | |
| IQ1_M | 7.9 GB | 8.6 GB | Too big | Get file → | |
| IQ2_XXS | 9.0 GB | 9.7 GB | Too big | Get file → | |
| IQ2_XS | 9.9 GB | 10.6 GB | Too big | Get file → | |
| IQ2_S | 10.1 GB | 10.8 GB | Too big | Get file → | |
| IQ2_M | 11.0 GB | 11.7 GB | Too big | Get file → | |
| Q2_K_S | 11.3 GB | 12.0 GB | Too big | Get file → | |
| Q2_K | 12.2 GB | 12.9 GB | Too big | Get file → | |
| IQ3_XXS | 12.8 GB | 13.5 GB | Too big | Get file → | |
| IQ3_XS | 13.6 GB | 14.3 GB | Too big | Get file → | |
| Q3_K_S | 14.3 GB | 14.9 GB | Too big | Get file → | |
| IQ3_S | 14.3 GB | 15.0 GB | Too big | Get file → | |
| IQ3_M | 14.5 GB | 15.1 GB | Too big | Get file → | |
| Q3_K_M | 15.7 GB | 16.3 GB | Too big | Get file → | |
| Q3_K_L | 17.0 GB | 17.6 GB | Too big | Get file → | |
| IQ4_XS | 17.5 GB | 18.2 GB | Too big | Get file → | |
| Q4_0 | 18.4 GB | 19.1 GB | Too big | Get file → | |
| Q4_K_S | 18.5 GB | 19.2 GB | Too big | Get file → | |
| Q4_K_M | 19.6 GB | 20.2 GB | Too big | Get file → | |
| Q4_1 | 20.4 GB | 21.0 GB | Too big | Get file → | |
| Q5_K_S | 22.3 GB | 23.0 GB | Too big | Get file → | |
| Q5_K_M | 22.9 GB | 23.6 GB | Too big | Get file → | |
| Q6_K | 26.4 GB | 27.1 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (7.23 GB, 7.9 GB memory at 8k context). For 12‑GB VRAM, use Q2_K (12.24 GB, 12.9 GB memory). For 24‑GB VRAM, use Q4_K_M (19.58 GB, 20.2 GB memory). Memory estimates are approximate.
What GPU do you need for Sarvam 30b Uncensored?
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: the best quant that fits is the main file (0.1 GB file, about 0.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.7 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_S (7.2 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q2_K_S (11.3 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (14.5 GB file, about 15.1 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (22.9 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (26.4 GB file, about 27.1 GB in use).
Which Sarvam 30b Uncensored quant should you choose?
Q4_K_M is the usual starting point for Sarvam 30b Uncensored: it balances file size and quality well. Here it is a 19.6 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sarvam 30b Uncensored
How much VRAM does Sarvam 30b Uncensored need?
About 20.2 GB at Q4_K_M with an 8K context window. That is the 19.6 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 Uncensored on an 8 GB GPU?
Yes, with IQ1_S: the 7.2 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sarvam 30b Uncensored GGUF?
It depends on the quant: file is 0.1 GB, IQ1_S is 7.2 GB, IQ1_M is 7.9 GB, IQ2_XXS is 9.0 GB, IQ2_XS is 9.9 GB, IQ2_S is 10.1 GB and 18 more.
What context length does Sarvam 30b Uncensored 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 Uncensored GGUF?
The files are on Hugging Face in the mradermacher/sarvam-30b-uncensored-i1-GGUF 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 Uncensored 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 Uncensored on 8 GB VRAM?
Yes, the IQ1_S quant uses 7.23 GB file size and requires about 7.9 GB memory at 8k context.
Does this model support vision or audio input?
No, the model only processes text and does not include vision or audio capabilities.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing modification and redistribution under its terms.