Marktechpost AI on X: "Cloudflare just released Clef and Clef-flash, its first in-house trained models: open-weight "decision models" that return typed probabilities instead of text. Clef is a 27B model built on Qwen3.8-27B. Clef-flash is a 9B model built on Qwen3.5-9B. Both ship under Apache 2.0. …
Quick Answer
Cloudflare has launched Clef and Clef-flash, its first in-house decision models, with Clef at 27B parameters and Clef-flash at 9B.
Quick Take
Both models utilize a unique prefill-only, non-autoregressive decision step, achieving significant performance metrics, including a median latency of 38.8 ms for Clef-flash, outperforming TypeSafe's Jev in several benchmarks.
Key Points
- Clef is a 27B model; Clef-flash is a 9B model.
- Both models are open-weight and licensed under Apache 2.0.
- Clef-flash achieves 38.8 ms median latency, significantly faster than Jev's 524.1 ms.
- Clef scores 94.20 on BANKING77, outperforming Jev's 79.74.
- Models support image/video input and have a 64K context window.
📖 Reader Mode
~1 min read
Cloudflare just released Clef and Clef-flash, its first in-house trained models: open-weight "decision models" that return typed probabilities instead of text. Clef is a 27B model built on Qwen3.8-27B. Clef-flash is a 9B model built on Qwen3.5-9B. Both ship under Apache 2.0. The core innovation is a prefill-only, non-autoregressive decision step. The frozen Qwen backbone runs 1 forward pass, then a small joint schema head routes evidence to each question and scores every option jointly. No tokens are generated, so there is nothing to parse. Training pairs rank-256 LoRA adapters with label-smoothed cross-entropy and a Brier loss for calibration, plus RLCD as a secondary objective. On Cloudflare's internal Decision Index run, Clef-flash posts a 38.8 ms median latency versus 524.1 ms for TypeSafe's Jev, and Clef scores 94.20 on BANKING77 versus Jev's 79.74. It is a strategic trade-off though: Jev still leads on knowledge-heavy tests like GPQA Diamond (78.3 vs 48.0) and MMLU-Pro (82.7 vs 65.9). With image and video input, a 64K context window and a Jev-compatible System One API, it is optimized for routing, triage and guardrails inside agentic workflows...... Full analysis: marktechpost.com/2026/10/01/clo… Model: huggingface.co/Cloudflare/clef Docs: developers.cloudflare.com/workers-ai/mod… @Cloudflare @michellechen
— Originally published at x.com
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from WebSearch (Tavily)
See more →全球AI芯片峰会，9月上海见！
The 2026 Global AI Chip Summit will take place in Shanghai on September 22-23, focusing on the evolving AI chip landscape, including the shift from training to inference, the rise of diverse chip technologies, and the restructuring of industry competition. Notable speakers include experts from leading universities and companies, discussing advancements in AI chip architecture and applications.