Clef Flash: 9B multimodal decision model fine-tuned from Qwen3.5, 256K context
ollama · x · 2026-10-03
Ollama shared details on Cloudflare's Clef Flash: a 9B multimodal decision model fine-tuned from Qwen3.5, supporting image inputs scored jointly with text state, 256K context window, requiring Ollama 0.35.1+.
It's fully compatible with the Jev and System One APIs, turning a state plus a typed-questions schema (instructions and true/false criteria) into decisions, with cURL, Python, and JavaScript examples in the docs.
Related event: Cloudflare's Clef Decision Models Now Available on Ollama(2 posts)→
More from Models
- Mystery 'iguana_necktie' Field Spotted in Anthropic Usage API — bytebot · 2026-10-03
- Insider teases 'new SSI model,' calling Ilya 'a truly remarkable human being' — iruletheworldmo · 2026-10-03
- Exploit Bench results are highly harness-sensitive: GLM 5.3 Flash beats 4.1, best in Claude Code — teortaxesTex · 2026-10-03
- Meta Muse quality collapsing: inference overload seen behind dropped tasks — brandon_galang · 2026-10-03
- vLLM releases open Decision 2.0 models: 64 questions in one pass at 63ms — vllm_project · 2026-10-03
- Why hasn't anyone trained a model on years of brilliant people's tweets? — Gauri_the_great · 2026-10-03