Michigan builders: K2 Horizon is coming to the University of Michigan this Saturday. ⛰️ Build with IFM’s open 375B-A23B flagship in the “Best Use of K2 Horizon” challenge. 🏆 100M tokens for every winning team member 📅 Sept. 19 | 9 AM–9 PM 📍 East Hall 1324 #K2Horizon# #OpenSource#

600+ CMU students. 39 teams. 24 hours of building with #K2Horizon#. 🚀 At #HackCMU# 2026, teams created everything from 3D design tools to food-planning and social apps. Congratulations to K2 Cascade, winner of the “Best Use of K2 Horizon” track! 🏆 Thank you, @nebiusai, for powering the compute behind our HackCMU sponsor track.

K2 Horizon got another llama.cpp-family path, this time through TurboQuant. Spark-X2.5 already landed in upstream llama.cpp. I’ve actually got it running myself. A brand-new K2 Horizon TurboQuant PR adds … 🧠 K2 Horizon model support 📦 Hugging Face → GGUF conversion 💬 tokenizer + chat templates ⚙️ llama.cpp-style inference And they’ve already tested 🧠 K2-Horizon-3.7B Q4_K_M 🍎 M3 Pro / 18GB ⚡ ~35 tok/s 📚 64K configured context The PR also adds Spark-X2.5 to the TurboQuant fork: ⚡ ~36 tps 📚 256K configured context Caveats ⚠️ This is still an OPEN PR ⚠️ Only Metal has been tested ⚠️ Other K2 sizes + MoVA/MoE variants remain untested K2 Horizon already has an IFM llama.cpp fork, but it still isn’t supported in normal upstream llama.cpp. So what I’m watching here is whether TurboQuant becomes another path for K2.

K2-Horizon-7B scores 21 on Artificial Analysis Intelligence Index, punching above its weights. It scores 50% above the next best model under 10B, beating Qwen3.6-35B-A3B and closely matching Qwen3.6-27B. • Try it: • 8-bit quantization: • Uno, the speed-up diffusion-augmented version:

K2 Horizon is coming to CMU. Following the release, we're hosting a workshop on building with K2 Horizon, followed by an event at HackCMU 2026. We look forward to seeing what CMU's hackers create. Learn more:

Meet K2 Horizon model fleet. The smallest model is designed for devices where memory, power consumption and local processing matter. The largest model is intended for demanding reasoning and enterprise AI workloads. Developers can prototype on smaller models and scale to larger models without leaving the K2 Horizon fleet. Start building:

Build on K2 Horizon. •⁠ ⁠Self-host all six models with vLLM or SGLang, weights on Hugging Face •⁠ ⁠Run locally with Ollama •⁠ ⁠Use it in OpenCode and OpenClaw •⁠ ⁠Deploy through our API platform Details in IFM developer doc: Download weights: Access API Keys:

Intelligence is too important to buy as a service and too fundamental not to own as a capability. K2 Horizon provides not only weights entities can hold, but a foundation they can build their own intelligence on without external dependencies. K2 Horizon is here to put that ownership in your hands: run it, inspect it, retrain it, keep it.