webAI released the TwIL-8B inference model
The story so far
webAI released the TwIL-8B inference model, based on IBM Granite 4.2 8B fine-tuning, achieving a score of 98.2 on MATH-500 and 81.6 on LiveCodeBench. The model's weights are released under a non-commercial license on Hugging Face, with a 4-bit quantized version being 4.98 GiB, suitable for CPUs or moderately memory-equipped GPUs. New reports indicate that TwIL-8B performs better than Gemma 4 31B in mathematical and programming tasks, with reasoning capabilities reaching 88~93% of cutting-edge models, but limited knowledge reserves. New reports also mention that TwIL-8B focuses on local small professional models, with its weights open-sourced under a non-commercial license agreement.
AI-written from the reports · Updated 13 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- ITHome · AIwebAI's Open Source TwIL-8B Inference Model: Focused on Mathematics and Programming, Outperforms Gemma 4 31B in Long Board Performance
webAI Launches TwIL-8B Inference Model, Optimized for Math and Code Tasks Based on IBM Granite-4.2-8B, Scores Better than Gemma 4 31B in MATH-500 and AIME 2025 Tests, Best in LiveCodeBench Group, IFBench on Par with Gemma 4 12B. Model Inference Capability Reaches 88~93% of Frontier Models, Reduces AI Usage Costs but Has Limited Knowledge Base.
- MarkTechPostwebAI Releases TwIL-8B, an 8.8B Reasoning Model Scoring 98.2 on MATH-500
webAI has released TwIL-8B, an 8.79B dense inference model fine-tuned based on IBM Granite 4.2 8B, achieving 98.2 on MATH-500 and 81.6 on LiveCodeBench†, using 38% fewer tokens than Qwen3.5-9B.