Ollama v0.35.1: Clef decision models
Clef decision models Ollama now supports Clef and Clef Flash, Cloudflare's new open-source decision models, through /v1/systemone. Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions…
Marked as a signal by the editors; worth tracking.
On this page11 sections
The editors' notes below — why it matters, the context, the learning path — are written in Chinese.
Record
The signal
#Clef decision models Ollama now supports Clef and Clef Flash, Cloudflare's new open-source decision models, through /v1/systemone. Clef (27B) and Clef Flash (9B) are multimodal: requests can now include images alongside the text state, shared by all questions and scored jointly with it. curl http://localhost:11434/v1/systemone -d '{ "model": "clef-flash", "state": "The user took this screenshot.", "images": ["<base64-encoded image>"], "questions": { "has_ollama": {"type": "noul", "instructions": "Does this image contain Ollama?"} } }' { "model": "clef-flash", "answers": { "has_ollama": { "type": "noul", "noul": 0.958 } }, "usage": { "input_tokens": 548, "output_tokens": 0 } } What's Changed Models using web search can now perform up to ten searches per response, up from three Modelfiles now support CAPABILITY declarations, so model creators can explicitly declare what a model can do. Declarations are preserved when creating from GGUF or safetensors, through model inheritance, and on Modelfile export ollama show and the model list now report only decision as the capability for decision models, so clients no longer offer them for general chat, tools, or thinking Updated llama.cpp and the MLX engine Full Changelog: v0.35.0...v0.35.1
Why now
Why it matters
#决策模型从 Jev 一家变成了 Clef、d1 三家，Ollama 也为它们开了专用接口。智能体里大量「选哪个、是不是、打几分」的调用，可以从生成模型换成一次前向的概率输出。
Background
Technical context
#普通语言模型逐个生成 token，决策模型只做一次前向，直接给出每个选项的概率，所以延迟低、输出可以直接解析。非自回归指不逐字生成。置信度是概率分布的集中程度，与准确率之间需要校准才能对应。
Audience
Who should care
#Next
Learning path
#- 先读本站 9 月 21 日的 Jev 信号，了解决策模型这一类的来历
- 读《模型选型与约束匹配》，列出自己系统里只需要选项输出的调用
- 用 Ollama 拉取 clef 或 clef-flash，在自己的分类数据上和现有做法对比
- 读《API 契约与接口边界》，想清楚 /v1/systemone 这类新接口怎么接入现有服务
Network
Where it sits in the network
#How this signal connects to neighbouring technologies, skills and background knowledge. Follow any link to keep exploring.
Further thought
Follow-up questions
#- 你的智能体里有多少调用其实只需要一个选项或一个分数？
- Clef、Clef Flash 与 Jev 在你的数据上谁更准？延迟差多少？
- 你会怎样把置信度校准成可用的准确率估计？
Publication record
Featured in
#The briefings that carried this signal, newest first; the last row is the weekly review of its week. The tag is the section it ran in.
技术简报 - 2026-10-08
Worth trackingWeekly review · Sep 28 – Oct 4
Worth tracking
Sources