AINewsnow

TwIL-8B vs Qwen3.5-9B: The 81.6 Code Score Isn't the GGUF You Download

An 8B model that scores 98.2 on MATH-500 and 81.6 on LiveCodeBench, and fits in a 4.98 GiB GGUF. That's the pitch for TwIL-8B , webAI's post-train of IBM's Granite 4.2 8B (8.8B parameters, per the card), and on paper it beats Qwen3.5-9B at both. I read the model card twice before writing this, and…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-09 00:30 · DEV Community — Machine Learning
    TwIL-8B vs Qwen3.5-9B: The 81.6 Code Score Isn't the GGUF You Download

More stories

  1. Nvidia opens investigation after CEO Jensen Huang admits to affair with alleged Chinese spy — Axios AI+
  2. US AI Safety Center CAISSI Asked to Report to White House, Raising Independence Concerns — AP News
  3. Hydra-PSIE expands 'Coeziune OM–IA' DOI registry to 39 published works — DEV Community — AI
  4. Earnings Calls Highlight AI Momentum at BCE, Doximity and N-able — The Globe and Mail
  5. Anthropic agrees $3.4 billion deal for gas-fired generators to power AI data centres — Financial Times AI
  6. Latest Hiring Data Shows No White-Collar Job Losses From AI Yet — Wall Street Journal Technology
  7. Voters reject AI data centers in midterms, sending tech stocks lower — Barron's
  8. Investor Comparisons Pit Nvidia Against AMD and Micron in AI Chip Race — The Globe and Mail

Get the daily brief of stories like this at 6:30 every morning →