Loading…
Your privacy choices
Necessary storage keeps the site working. Analytics and advertising stay off unless you allow them. Cookie notice
EPFL-LARA
AI for mathematics, including formal mathematics and theorem proving in Lean, and AI for verified software engineering.
- Develops
- 7 model versions
Model families and versions
Every model version this company develops, newest first; each links to its own model card.
1–7 of 7
| Model | Released | Context window | Weights | Licence |
|---|---|---|---|---|
| Lean World Model Qwen3 4B Grpo | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| Lean World Model Qwen3 8B Reasoning Grpo | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| Lean Standard Prover Qwen3 8B Reasoning Grpo | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| Lean World Model Qwen3 8B Sft | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| Lean Standard Prover Qwen3 8B Grpo | ||||
| Lean World Model Qwen3 8B Grpo | 32,768 tokens Per Hugging Face; not confirmed by the developer | |||
| Lean Standard Prover Qwen3 8B Sft | 32,768 tokens Per Hugging Face; not confirmed by the developer |
Pricing
Offers this company serves as a provider, whoever developed the model. Each price uses the currency and billing unit shown with it.
EPFL-LARA serves no priced offer itself.