clef models: 256k context, ~13x faster than Jev, open source under Apache 2.0
dinasaur_404 · x · 2026-10-02
michellechen highlights the distinguishing features of the clef model family:
- Vision encoder supports image classification, not just text
- Trained for 256k context (64k in the hosted version)
- clef-flash is roughly 13x faster than Jev, with drop-in Jev API compatibility
- Open source under Apache 2.0, hosted on Workers AI leveraging edge GPUs for latency
- Ships with a new RL platform for fine-tuning on your own data
Related event: Cloudflare Open-Sources Decision Models clef and clef-flash(10 posts)→
More from Models
- Nat Eliason suspects @bot now runs on 4.7, says he reaches for Claude and Codex less — nateliason · 2026-10-02
- Users report queries being routed to Fable 5.5, with SVG tests said to far beat 5.1 — kimmonismus · 2026-10-02
- 180B Qwen model runs on one DGX Spark: 2.39-bit quant keeps 95.5% of BF16 scores — TheZachMueller · 2026-10-02
- Grok 4.7 reportedly live across all modes in the Grok app — XFreeze · 2026-10-02
- Claude's cloud sessions don't cost extra — bonus credits are cloud-only tokens — stablequan · 2026-10-02
- One 'please continue' Prompt Burned a 5-Hour Usage Cap in 6.5 Minutes — thawingfrog · 2026-10-02