Open Models
Sthānika AI (“of this place”) is a research lab building specialist, fine-tuned open models — released with weights, datasets, benchmarks, and papers.
100% Local
Built for this place and small enough to run on your own machines.
A small model fine-tuned on the right data outperforms frontier models on its task — at a fraction of the cost. We target where frontier models are structurally weak: code-mixed Indian languages, India-specific domains, on-premise deployment.
Every project ships its weights, its curated dataset, and its expert-graded benchmark. Reproducibility is the product.
No model trains before its evaluation set exists. Every claim on this site traces to a published benchmark, powered by our open evaluation harness and benchmarks.
// 01 — adapters
fine-tuned weights · open inference
A LoRA adapter for unsloth/gemma-3-12b-it, fine-tuned to answer Indian farmers' crop-advisory questions in the style of Kisan Call Centre (KCC) responses — in English and 10 Indian languages. Scores 3.44 in correctness on the Indic-KCC-Agri-Advisory-Benchmark, beating the unmodified 12B base by +1.36 and edging past gemma-3-27b-it, a base model with more than 2× the parameters.
// 02 — writing
every claim traces to a published benchmark
21 models answered 1,084 BKP-500 items across seven India-specific knowledge categories, each paired with an international control twin so the India gap is measured rather than assumed. Qwen3.6 27B leads at 53.2% Bharat Score; Sarvam-M 24B is the strongest India-built model.
500 real crop-advisory questions from the Kisan Call Centre, asked in 11 Indian languages and graded by an LLM judge. DeepSeek V4-Flash leads at 4.29 out of 5; among open-weight models, Gemma 3 27B and Qwen3.6 27B tie at 3.26.
Eight open-weight vision-language models read every legible sign in 1,319 unedited photographs from across India — full frames, no crops, 13 language labels. The decisive gap is not between models but between scripts: on the 914 images carrying both, every model reads the English better than the Indic text beside it.
16 AI models asked the same 1,024 general-knowledge questions and 955 maths problems five ways — English, Hinglish, Hindi, and their romanized forms. Writing in English letters costs more than mixing languages does, and the two costs compound.
Telugu, Hindi, Kannada, Marathi, Hinglish, and English across Gemma, Qwen, Mistral-Tekken, and OpenAI's cl100k/o200k. Modern tokenizers sit within ~10% of each other on Indic — but the previous generation pays 2–4×. Dravidian languages cost ~4–5 tokens per word everywhere; plan serving budgets accordingly. Sentence set and scripts released.
We benchmarked 17 models on the complete MILU test set — 79,608 questions across 11 languages, with no subsampling — and put a real cost-per-rupee lens next to raw accuracy. Qwen3.8-Max leads at 89.67%; DeepSeek V4-Flash lands 3rd at ₹2.45 per 1,000 answered questions.
// 03 — changelog
announcements · coverage · talks
// 04 — the lab
Sthānika AI is the research lab of PurpleTalk — a twenty-year digital innovation company headquartered in Hyderabad. Where PurpleTalk builds products, Sthānika publishes research: small, specialist models built with partners who hold deep domain knowledge — seed companies, hospitals, diagnostics chains, public institutions — under one covenant: the general capability is released open; the partner's proprietary edge stays theirs.
The aim: to be the lab India's institutions trust with the models that run closest to their people.
# research ships into real products through the family
// 05 — open door
You hold the domain knowledge and the data exhaust; we build the model. Open front door, private deep end.
$ propose_partnership→Sovereign, on-premise, open-weight deployments — evaluated in the open.
$ start_conversation→