Cloudflare's clef, a Qwen3.8-based image-text-to-text model, trends on Hugging Face
Cloudflare · hf · 2026-10-02
Cloudflare's clef model is trending on Hugging Face as an image-text-to-text model. Tags indicate it is a post-trained model built on the Qwen3.5/Qwen3.8 architecture with image-text-to-typed-output support, released in safetensors format and loadable via transformers. Details remain thin pending the full model card.
Related event: Cloudflare Open-Sources Decision Models clef and clef-flash(10 posts)→
More from Models
- Burkov: on truly novel problems, LLM error rates tell you how often you'll be fooled — burkov · 2026-10-02
- OpenAI Still Leads by a Solid Margin on Model Benchmark, Third-Party Notes — steipete · 2026-10-02
- Grok 4.7 now available on the Gemini Enterprise Agent Platform — SpaceXAI · 2026-10-02
- JevBench adds configurable cost tolerance: different budgets, different winners — airesearch12 · 2026-10-02
- IFM Open-Sources K2 Horizon: Six Fully Open Models from 0.9B to 375B — aya-ifm · 2026-10-02
- No open models in top 25 anymore: MiMo #26, Qwen #28, GLM #30 — teortaxesTex · 2026-10-02