Ivan Zhang

Trying to get @__tinygrad__ running with my m4 mini and a 5070 Seeing if it’ll run with a decent enough modem for Hermes Agent from @NousResearch Don’t know if 12gb is going to cut it

Here's how anyone can find models that work for your hardware easily. 1. Go to huggingface.co and make an account 2. Models tab to find weights and all compressions 3. Click on your profile on the top right.

github.com/safrano9999/op… Wrapper Server in Python to use MLX DFlash with Qwen3.5 and Qwen3.6 local llm on Apple Silicon. Tested with @NousResearch Hermes and @openclaw @zhijianliu_

🔥 DFlash x MLX is happening! Shoutout to @aryagm01 for the early work on this. We're building on the momentum. Native MLX support, more models (Qwen3.5), up to 4x faster. Lossless! 👉 github.com/z-lab/dflash

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…