# Is Vemana SOTA?

Pending benchmarks. Announced Oct 27, 2026; no independent results yet.

As of Nov 3, 2026, Vemana is pending benchmarks on isitsota: announced Oct 27, 2026, with no independent results on the boards we track yet.

Udgam Labs' 278M-parameter Telugu base model, trained from scratch with its own Telugu tokenizer and released under Apache-2.0. It continues Telugu text (it does not follow instructions) and runs on a laptop CPU or in a browser tab.

Canonical: https://isitsota.com/m/vemana
Last updated: 2026-10-27
Tracking since: 2026-10-27

## Announced facts

| Fact | Value |
| --- | --- |
| Lab | Udgam Labs |
| Announced | Oct 27, 2026 |
| API | Not yet |
| Open weights | Published |
| Parameters | 278M (278,214,144) |
| Type | Base model: continues Telugu text; no instruction or safety tuning |
| Architecture | Gemma 4 text layout (Gemma4ForCausalLM): 18 layers, width 1,024, 8 query and 2 key-value heads, full attention, tied embeddings |
| Tokenizer | Its own 32,000-token Telugu tokenizer with byte fallback |
| Context | 1,024 tokens (the length it was trained at) |
| Training data | 5.1B unique tokens of public Telugu web text from Sangraha (AI4Bharat), FineWeb-2 and HPLT 3.0, read about 2.35 times (12.0B token positions) |
| Training run | From random initialization on one H100 in about 16 hours, Oct 26-27, 2026, streamed live |
| Release | Vemana-Base weights, every 10% checkpoint (Vemana-Checkpoints), GGUF Q8_0 (297 MB) and F16 (558 MB), and the evaluation code on GitHub |
| Browser demo | Runs fully in the browser tab on udgamlabs.com (297 MB download, text stays on the device); also a Hugging Face Space |
| License | Apache-2.0 |

Tags marked unsure are not stated on the lab's own pages.

## What would let us call it

Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.

- [x] Publicly announced with a source
- [x] Usable by the public (API or weights)
- [ ] Listed on an independent board we track
- [ ] Enough results for a rank in a category
- [ ] Holds across two snapshots (crowns only)

## What the lab claims

Self-reported. Shown for context; not used in any verdict.

- Lab claim: about $69 of GPU time for the training run.
- Lab claim: 0.361 bits per byte on 416 Telugu Wikipedia pages from Sep-Oct 2026, ahead of every other open base model under 1B it tested, including nanochat-telugu-560M (0.383); Sarvam-1 (2.5B) scores 0.356.
- Lab claim: 0-shot Belebele-te 25.1%, MILU-te 25.3%, IndicXNLI-te 35.0%, IndicCOPA-te 58.4%, which the lab reports as at or near chance.
- Lab claim: about 65 tokens per second on a Mac mini CPU.

## Sources

- LAB: [Vemana, a small Telugu model trained live in public (Udgam Labs blog)](https://udgamlabs.com/blog/vemana) (2026-10-27)
- LAB: [Vemana model page with in-browser demo (Udgam Labs)](https://udgamlabs.com/models/vemana) (2026-10-27)
- PAPER: [Vemana: a 278M Telugu language model trained from scratch (technical report)](https://udgamlabs.com/research/vemana) (2026-10-27)
- REPO: [udgamlabs/Vemana-Base on Hugging Face](https://huggingface.co/udgamlabs/Vemana-Base) (2026-10-27)
- REPO: [udgamlabs/vemana on GitHub](https://github.com/udgamlabs/vemana) (2026-10-27)
- LAB: [Jitesh K Prasad (Udgam Labs) on X: Vemana release](https://x.com/jiteshkprasad/status/2115025372723151272) (2026-10-27)

Tracking continues until an independent board lists it.

## Related

- Lab: [Udgam Labs](https://isitsota.com/labs/udgam-labs.md)
- All pending releases: https://isitsota.com/releases.md
- JSON: https://api.isitsota.com/v1/models/vemana