Apple drops new HF model: Qwen3.5-9B finetune that turns long docs into page images to save tokens
yoobinray · x · 2026-09-25
Apple quietly released a new open model on Hugging Face: a Qwen3.5-9B finetune that compresses long documents into small page images to save tokens, then retrieves the full text of only the pages relevant to the user's question. The hybrid visual-compression approach aims to cut long-context processing costs while keeping access to exact original text.
Related event: Apple Open-Sources LensVLM-9B for Token-Efficient Long-Document QA(5 posts)→
More from Models
- Opus 5.5 feels nerfed — user blames system prompt restrictions, not the model — oyacaro · 2026-11-12
- ChatGPT now links to brand homepages far more, reshaping brand-mention tracking — lilyraynyc · 2026-11-12
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
- ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12
- LMArena Launches Agent Arena for Head-to-Head Agent Evaluation — arena · 2026-11-12