Cloudflare open-sources Clef decision models, half the latency of Jev
Cloudflare Blog · rss · 2026-10-01
Cloudflare released Clef and Clef-flash, open-source (Apache 2.0) decision models on Workers AI, plus an RL fine-tuning platform. Built on Qwen with a non-autoregressive scoring pass, Clef leads most Jev Decision Index benchmarks with median latency of 209ms (Clef) and 38.8ms (Clef-flash) vs Jev's 524ms. It adds a vision encoder and 64k context (Jev: text-only, 32k), stays Jev-API compatible, and ships with an FDE-assisted fine-tuning service.
More from Infra
- tandem.cpp v0.3.0: 2-6x faster prefill for models too big for VRAM, Maya DeepSeek-V4.1 support — smflx · 2026-11-16
- Developers poll real costs of running coding agents on remote VMs for work — radim11 · 2026-11-16
- Datadog's new gateway returns 402 when a model's budget runs out—so agents just retry — YvesMulkers · 2026-11-16
- Max-quality local Minimax H3 video on a 4090: community-tested int8 setup — newaccount47 · 2026-11-16
- Local V2V outfit transfer on a 16GB M3 MacBook Air: 15.7 min cut to 2.4 min — might_thinker · 2026-11-16
- FlashStates hits 3.14x vLLM prefill throughput for hybrid-architecture agentic inference — 机器之心 · 2026-11-16