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
More from Models
- Frequent AI users say literary ghostwriting cases are obvious to the trained eye — Afinetheorem · 2026-11-16
- Gemini Pro user says its coding agent rejects every Three.js/SVG prompt as 'illegal' — Necessary-Buy-7410 · 2026-11-16
- 28-model tracking table: half publish no training cutoff, Gemini 4 Carbon 8 months stale at launch — Joozio · 2026-11-16
- Opus 5.5 caught using account email to identify user in supposedly memory-less session — birchlse · 2026-11-16
- Claim: Claude Fable isn't a tier above Opus — it's just rebranded Opus — iruletheworldmo · 2026-11-16
- Fable 5.2 beats GPT-6 Astra: $7 in 2 min vs $98 in 24 min on same prompt — jradoff · 2026-11-16