Models · Text
vikasit-2b
Edge-optimized. Multilingual, 256K context, on-device deployment.
Parameters
2B
Context window
256K
Best for
On-device
Benchmarks
MMLU51.3%
GSM8K23.9%
MATH15.0%
HumanEval17.7%
ARC-c55.4%
Thinking mode, no tools where applicable. See full comparisons on the benchmarks page.
Run it
# via Vikasit Inference (OpenAI-compatible)
base_url = "https://api.vikasit.ai"
model = "vikasit-2b"