agaram 2.5b needs about 4.2 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 3 quants, from 1.6 GB (Q4_K_M) to 5.1 GB (F16).
Agaram 2.5B – Tamil–English chat model in GGUF format
Agaram 2.5B is a 2.53‑billion‑parameter Llama‑based model trained from scratch by Murai Labs. It supports Tamil script, romanized Tamil, and English, and can translate between Tamil and English. The model is available in GGUF for llama.cpp with tool‑call support.
Good at
- Tamil–English translation
- Chatting in Tamil script
- Tool‑call integration
Limits
- No vision support
- Requires 8 k context for full memory estimate
- Apache‑2.0 license
Best for
- Local Tamil chat assistants
- Tamil–English translation tools
- Tool‑enabled LLM applications
Who it’s for. Developers building local Tamil language assistants or translation services. Researchers needing a non‑fine‑tuned Tamil–English model for experimentation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 1.6 GB | 4.2 GB | Fits | Get file → | |
| Q8_0 | 2.7 GB | 5.3 GB | Fits | Get file → | |
| F16 | 5.1 GB | 7.7 GB | Tight | Get file → |
For 8 GB VRAM, use the Q4_K_M quant (1.56 GB file, ~4.2 GB memory at 8 k context). For 16 GB VRAM, Q8_0 (2.69 GB file, ~5.3 GB memory) or F16 (5.06 GB file, ~7.7 GB memory) provide higher precision. Memory estimates are approximate.
What GPU do you need for agaram 2.5b?
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: the best quant that fits is Q8_0 (2.7 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is F16 (5.1 GB file, about 7.7 GB in use).
Which agaram 2.5b quant should you choose?
Q4_K_M is the usual starting point for agaram 2.5b: it balances file size and quality well. Here it is a 1.6 GB file.
The Q8_0 file is 2.7 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about agaram 2.5b
How much VRAM does agaram 2.5b need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.6 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 agaram 2.5b on an 8 GB GPU?
Yes, with F16: the 5.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of agaram 2.5b GGUF?
It depends on the quant: Q4_K_M is 1.6 GB, Q8_0 is 2.7 GB, F16 is 5.1 GB.
What context length does agaram 2.5b support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.1 GB at 8K and 2.1 GB at 8K.
Where can I download agaram 2.5b GGUF?
The files are on Hugging Face in the murai-labs/agaram-2.5b-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 agaram 2.5b 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 Agaram 2.5B on 8 GB VRAM?
Yes, the Q4_K_M quant uses 1.56 GB file and requires about 4.2 GB memory at 8 k context.
Does Agaram 2.5B support vision?
No, the model has no vision capabilities.
What license is Agaram 2.5B released under?
It is released under the Apache‑2.0 license.