Stage Vemana Base needs about 0.9 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.3 GB (Q8_0) to 0.6 GB (F16).
278M‑parameter Telugu language model
Stage Vemana Base is a 278M‑parameter Telugu model trained from scratch on 5.1B public Telugu web tokens. It continues Telugu text and does not follow instructions. The model runs on a laptop‑class CPU.
Good at
- Telugu text continuation
- Low‑resource inference
- Fast token generation on CPU
Limits
- No instruction following
- No vision support
- Context limited to 1,024 tokens
Best for
- Generating Telugu stories
- Local Telugu text completion
- CPU‑based inference on laptops
Who it’s for. Developers needing a lightweight Telugu language model for local inference. Researchers testing Telugu language generation without instruction tuning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 0.3 GB | 0.9 GB | Fits | Get file → | |
| F16 | 0.6 GB | 1.1 GB | Fits | Get file → |
For 8 GB VRAM, use the Q8_0 quantized file (0.3 GB, ~0.9 GB memory at 8k context). For 4 GB VRAM, the F16 quantized file (0.56 GB, ~1.2 GB memory at 8k context) is the only option. Memory estimates are approximate.
What GPU do you need for Stage Vemana Base?
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 F16 (0.6 GB file, about 1.2 GB in use).
Which Stage Vemana Base quant should you choose?
Q8_0 (0.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Stage Vemana Base
How much VRAM does Stage Vemana Base need?
About 0.9 GB at Q8_0 with an 8K context window. That is the 0.3 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 Stage Vemana Base on an 8 GB GPU?
Yes, with F16: the 0.6 GB file needs about 1.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Stage Vemana Base GGUF?
It depends on the quant: Q8_0 is 0.3 GB, F16 is 0.6 GB.
What context length does Stage Vemana Base support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 4K.
Where can I download Stage Vemana Base GGUF?
The files are on Hugging Face in the udgamlabs/Vemana-Base-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 Stage Vemana Base 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 Stage Vemana Base on 8 GB VRAM?
Yes, the Q8_0 quantized file is 0.3 GB and requires about 0.9 GB memory at 8k context, fitting comfortably in 8 GB VRAM.
Does the model support instruction following?
No, Stage Vemana Base is a base model and does not follow instructions.
What context length can I use?
The model was trained at 1,024 tokens; keep prompts and outputs within this limit for best results.