Sarvam M needs about 16.2 GB of memory at Q4_K_M (a 14.3 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 26 quants, from 7.2 GB (IQ2_XS) to 47.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Sarvam M – a 23.6B multilingual reasoning model
Sarvam M is a 23.6B parameter language model built on Mistral‑Small. It is post‑trained for Indian languages and advanced reasoning. The model supports a hybrid think mode for complex tasks and a non‑think mode for general conversation.
Good at
- Advanced reasoning in math and coding
- Strong performance on Indian language benchmarks
- Hybrid think/non‑think mode
Limits
- No vision support
- Requires 32768 token context
- Apache‑2.0 license
Best for
- Complex math problem solving
- Programming assistance
- Multilingual Indic conversation
Who it’s for. Developers and researchers needing a large, multilingual reasoning model with strong Indian language support. The model is suitable for applications that require logical reasoning and coding help in both English and Indic languages.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XS | 7.2 GB | 9.0 GB | Too big | Get file → | |
| IQ2_S | 7.5 GB | 9.3 GB | Too big | Get file → | |
| IQ2_M | 8.1 GB | 10.0 GB | Too big | Get file → | |
| Q2_K | 8.9 GB | 10.7 GB | Too big | Get file → | |
| IQ3_XXS | 9.3 GB | 11.1 GB | Too big | Get file → | |
| Q2_K_L | 9.5 GB | 11.4 GB | Too big | Get file → | |
| IQ3_XS | 9.9 GB | 11.7 GB | Too big | Get file → | |
| Q3_K_S | 10.4 GB | 12.2 GB | Too big | Get file → | |
| IQ3_M | 10.7 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.5 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 12.4 GB | 14.2 GB | Too big | Get file → | |
| IQ4_XS | 12.8 GB | 14.6 GB | Too big | Get file → | |
| Q3_K_XL | 13.0 GB | 14.8 GB | Too big | Get file → | |
| IQ4_NL | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_0 | 13.5 GB | 15.3 GB | Too big | Get file → | |
| Q4_K_S | 13.5 GB | 15.4 GB | Too big | Get file → | |
| Q4_K_M | 14.3 GB | 16.2 GB | Too big | Get file → | |
| Q4_K_L | 14.8 GB | 16.7 GB | Too big | Get file → | |
| Q4_1 | 14.9 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 16.3 GB | 18.1 GB | Too big | Get file → | |
| Q5_K_M | 16.8 GB | 18.6 GB | Too big | Get file → | |
| Q5_K_L | 17.2 GB | 19.0 GB | Too big | Get file → | |
| Q6_K | 19.3 GB | 21.2 GB | Too big | Get file → | |
| Q6_K_L | 19.7 GB | 21.5 GB | Too big | Get file → | |
| Q8_0 | 25.1 GB | 26.9 GB | Too big | Get file → | |
| BF16 | 47.2 GB | 49.0 GB | Too big | Get file → |
For 8 GB VRAM, use IQ2_XS (7.21 GB) or IQ2_S (7.48 GB). For 16 GB VRAM, use Q4_K_M (14.33 GB) or Q5_K_S (16.3 GB). For 32 GB VRAM, use Q6_K (19.35 GB) or Q8_0 (25.05 GB). Memory estimates are approximate.
What GPU do you need for Sarvam 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 IQ3_XS (9.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_S (13.5 GB file, about 15.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K_L (19.7 GB file, about 21.5 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (25.1 GB file, about 26.9 GB in use).
Which Sarvam M quant should you choose?
Q4_K_M is the usual starting point for Sarvam M: it balances file size and quality well. Here it is a 14.3 GB file.
The Q8_0 file is 25.1 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ2_XS at 7.2 GB, with the quality trade-offs that come with fewer bits. 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 M
How much VRAM does Sarvam M need?
About 16.2 GB at Q4_K_M with an 8K context window. That is the 14.3 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 M on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Sarvam M GGUF?
It depends on the quant: IQ2_XS is 7.2 GB, IQ2_S is 7.5 GB, IQ2_M is 8.1 GB, Q2_K is 8.9 GB, IQ3_XXS is 9.3 GB, Q2_K_L is 9.5 GB and 20 more.
What context length does Sarvam M support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Sarvam M GGUF?
The files are on Hugging Face in the bartowski/sarvamai_sarvam-m-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 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 M on 8 GB VRAM?
Yes, use the IQ2_XS or IQ2_S quantizations, which are 7.21 GB and 7.48 GB respectively.
Does Sarvam M support vision tasks?
No, Sarvam M is a text‑only model with no vision capability.