Models & Labs
Cloudflare's Clef 27B Decision Model on Ollama
Ollama Bloghigh confidence
Why it matters
- →Provides an open-source alternative for low-latency, structured decision-making workflows.
- →Single-pass architecture offers potential speed advantages over autoregressive LLMs for classification tasks.
- →Apache 2.0 licensing allows unrestricted commercial use and integration into proprietary systems.
Cloudflare has made its Clef model available on Ollama's cloud and local infrastructure. The 27B parameter model, fine-tuned from Qwen3.8-27B, is designed for multimodal decision-making rather than general text generation. It accepts text and image inputs to produce structured outputs like routing decisions or policy checks in a single inference pass. Released under the Apache 2.0 license, Clef aims to outperform competitors like Jev on latency and accuracy benchmarks for specific workflow tasks.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1Gemma 4 Boosts Speed with Multi-Token Prediction
Ollama Blog · June 29, 2026 · Background
- 2Cloudflare unveils Kitesurf browser for AI agents
TechCrunch AI · August 7, 2026 · Background
- 3Together AI Enables A/B Testing for LLMs
Together AI Blog · August 17, 2026 · Background
- 4Qwen3.8-27B Model Explored and Optimized
Sam Witteveen · August 18, 2026 · Background
- 5Granite 4.2 LLMs Introduced by IBM and Hugging Face
Hugging Face Blog · August 25, 2026 · Background
- 6llama.cpp enables chunked prefill for causal rerankers
llama.cpp Releases · September 28, 2026 · Background
- 7Ollama adds Jev-style decision models
Ollama Blog · September 29, 2026 · Related
- 8llama.cpp v0.6.0 adds decision model API and Apple Silicon speedups
llama.cpp Releases · October 6, 2026 · Background
More in Models & Labs
Models & Labsmodels
llama.cpp b12029 adds CUDA 13 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally supporting NVIDIA's latest CUDA 13 stack alongside AMD's ROCm 10.0. The inclusion of native builds for Linux arm64 with Snapdragon chips, covering CPU, Adreno GPU, and Hexagon NPU, signals a serious push into mobile edge deployment. While Apple Silicon KleidiAI is disabled in this specific build, the broader hardware coverage means developers no longer need to compile from source for most modern accelerators. It’s less about new features and more about removing friction for anyone running local models on bleeding-edge or diverse hardware.
llama.cpp Releases
© The Verge AIModels & Labsother
Apple Intelligence arrives in China via iOS 27.3
Apple is finally unlocking its AI suite for Chinese users with the iOS 27.3 beta, marking a significant regulatory milestone after months of approval delays. The rollout relies on Alibaba’s Qwen model rather than OpenAI, integrating features like notification summaries and visual intelligence directly into the OS. By sidestepping the new Siri in favor of established text and image tools, Apple is prioritizing immediate utility over the full generative experience. This move effectively brings Apple’s AI capabilities to a massive new market, albeit with localized constraints that distinguish it from the global release.
The Verge AI
© Matt WolfeModels & Labsmodels
Google Releases Gemini 4 Carbon for Cost-Efficient Inference
Google launched Gemini 4 Carbon, a new model variant aimed at providing high performance at a lower cost for inference tasks.
Matt Wolfe