sarvam 105b GGUF IQ2 M IQ1 M needs about 30.9 GB of memory at IQ1_M (a 27.1 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 3 quants, from 0.3 GB to 37.3 GB (IQ2_M).
Sarvam‑105B GGUF with 2‑bit IQ2_M and 1‑bit IQ1_M quantizations
Sarvam‑105B is a 106‑billion‑parameter model based on the deepseek2 architecture. It supports a 131072‑token context and is released under the Apache‑2.0 license. The model is available in three GGUF files: an unknown quant, IQ1_M, and IQ2_M.
Good at
- Large‑context reasoning
- Indian‑language performance
- Agentic tasks
Limits
- No vision support
- Requires 8‑k context for memory estimates
- Large VRAM needed for full‑precision
Best for
- Chat applications with long context
- Code generation in Indian languages
- Research on MoE models
Who it’s for. Developers and researchers needing a high‑capacity reasoning model with extensive context. The model is suitable for those who can allocate sufficient GPU or RAM resources and are comfortable with GGUF formats.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ1_M | 27.1 GB | 30.9 GB | Too big | Get file → | |
| IQ2_M | 37.3 GB | 42.2 GB | Too big | Get file → |
For 8‑GB VRAM, the IQ1_M file (27.11 GB) is the smallest option, but it will still need additional RAM to hold the model. The IQ2_M file (37.25 GB) offers higher quality at the cost of more memory. The unknown quant file (0.34 GB) is the lightest but lacks precision details.
What GPU do you need for sarvam 105b GGUF IQ2 M IQ1 M?
These figures add the file size, an fp16 KV cache at an 8K context window 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 (0.3 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.9 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.9 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (0.3 GB file, about 0.9 GB in use).
- 32 GB VRAM: the best quant that fits is IQ1_M (27.1 GB file, about 30.9 GB in use).
- 48 GB VRAM: the best quant that fits is IQ2_M (37.3 GB file, about 42.2 GB in use).
Which sarvam 105b GGUF IQ2 M IQ1 M quant should you choose?
IQ1_M (27.1 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.
If memory is tight, the smallest file is the first one in the table at 0.3 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 105b GGUF IQ2 M IQ1 M
How much VRAM does sarvam 105b GGUF IQ2 M IQ1 M need?
About 30.9 GB at IQ1_M with an 8K context window. That is the 27.1 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 105b GGUF IQ2 M IQ1 M on an 8 GB GPU?
Yes, with the smaller files: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of sarvam 105b GGUF IQ2 M IQ1 M GGUF?
It depends on the quant: file is 0.3 GB, IQ1_M is 27.1 GB, IQ2_M is 37.3 GB.
What context length does sarvam 105b GGUF IQ2 M IQ1 M support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download sarvam 105b GGUF IQ2 M IQ1 M GGUF?
The files are on Hugging Face in the Aaravomega/sarvam-105b-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 105b 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 the IQ2_M quant on 8 GB VRAM?
The IQ2_M file is 37.25 GB; 8 GB VRAM alone is insufficient. You would need to split the model between GPU and system RAM or use a larger GPU.
Is the model compatible with llama.cpp?
Yes, the GGUF files are designed for llama.cpp and can be loaded with a recent build.
Does the model support vision?
No, the model has no vision capabilities.