Skip to content

Beta: real launches, updated every morning. Rankings may change while we tune them.

TwIL 8B

An 8.8B reasoning model for math, code and instruction following, post-trained from ibm-granite/granite-4.2-8b with full-parameter supervised fine-tuning and GRPO/DAPO reinforcement learning. It ships in two variants that share one architecture and tokenizer: balanced (the default) and verbose. See Variants. Against open models of similar size and up to 3.5x larger, TwIL-8B posts the highest MATH-500 (98.2) and LiveCodeBench (81.6 †) scores in the comparison and leads Qwen3.5-9B on IFBench (+9.9 †). It is level with Qwen3.5-9B on contest math while using fewer tokens per problem.

48Rank on 12 November 2026Down 2 places from 11 Nov

TwIL 8B launched on 14 October 2026. It ranked #48 on Daily Launch on 12 November 2026 with a Launch Score of 31, from trending score 225 on Hugging Face. It moved down 2 places from the day before.

Visit siteTrending on Hugging Face · trending score 225, 316 likes
Share

What is TwIL 8B?

TwIL 8B is a model by webAI-Official on Hugging Face. It is released under the webai-non-commercial-license-ver.-1.0 license.

How to get TwIL 8B

Get it from its model card on Hugging Face.

Daily Launch card for TwIL 8B

Launch timeline

  1. Hugging FacePublished on Hugging Face

  2. Hugging FaceTrending score 211, ranked #55 on Daily Launch

  3. Hugging FaceTrending score 236, ranked #55 on Daily Launch

  4. Hugging FaceTrending score 256, ranked #39 on Daily Launch

  5. Hugging FaceTrending score 270, ranked #46 on Daily Launch

  6. Hugging FaceTrending score 225, ranked #48 on Daily Launch

Launch Score, last 7 days

0501006 Nov: 06 Nov7 Nov: 07 Nov8 Nov: 388 Nov9 Nov: 389 Nov10 Nov: 4810 Nov11 Nov: 4411 Nov12 Nov: 3112 Nov31 12 Nov
Launch Score, 0 to 100. Days it was not ranked show 0.

#83 of 228 in the roundup for the week of 9-15 November 2026.

Similar new launches