跳到正文
𝕏 Rohan Paul(x.com)·· 17 天前品質評分48
重點導讀

webAI 開源 TwIL-8B,這款以 IBM Granite 4.2 8B 為基礎打造的 8.8B 模型,針對數學、程式設計與指令遵循訓練。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

Rohan Paul
Rohan Paul@rohanpaul_ai
·17 天前
𝕏

webAI (@thewebAI) just open-sourced TwIL-8B, an 8.8B model built on IBM’s Granite 4.2 8B and trained for math, coding and following instructions.

> TwIL-8B fits in a 4.98 GiB quantized file that runs on a CPU or modest graphics card, putting near-frontier coding and math on hardware people already own.

> scores 81.6% on LiveCodeBench, 16.0 points above Qwen3.5-9B and ahead of Google’s Gemma 4 31B, a model 3.5x its size.

> Against GPT-5.5, Claude Opus 4.8 and Grok 4.3, TwIL-8B reaches 93% of the best frontier score on coding and 92% on instruction following, beating Claude Opus 4.8 on IFBench by 12.2 points.

> A final training stage that rewards shorter reasoning lets TwIL-8B solve AIME 2026 problems with 38% fewer tokens than Qwen3.5-9B, while posting the highest MATH-500 score in its comparison at 98.2%.

推文來源 · X (Twitter)在 X 參與討論

讀者討論

理性交流 · 即時討論