Local Ai
Qwen3.8-27B, up to 144 tok/sec on M5 Max. Let that sink in. ⚡️✨🚀 Excited to partner with @inco_ai to bring you their Splash inference engin…
Qwen3.8-27B, up to 144 tok/sec on M5 Max. Let that sink in. ⚡️✨🚀 Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0! Get it running now: https://lmstudio
Qwen3.8-27B, up to 144 tok/sec on M5 Max. Let that sink in. ⚡️✨🚀 Excited to partner with @inco_ai to bring you their Splash inference engine in LM Studio on day 0! Get it running now: https://lmstudio.ai/blog/splash-engine Qwen3.8-27B at 144 tok/s on an M5 Max MacBook Pro ⚡ Meet Inco Splash: our open-source inference engine, built around the model and around Apple silicon. Up to 3× the decode speed of Ollama, 2× oMLX, and almost 4× when an agent fans out into sub-agents.
Related
- Dive into the docs to get started: https://lmstudio.ai/docs/integrations/openclaw
- We made @lmstudio's MLX Engine a lot faster in the latest release. Read the technical deep dive from @ostensiblyneil. P.S. it's all open sou…
- LM Studio on stage for WWDC at the Steve Jobs Theater demonstrating MLX distributed on 4 Mac Studio! Coming later this year @lmstudio 👾
- 🦞👾 LM Studio is now an official @openclaw provider! Run: openclaw onboard --auth-choice lmstudio Use your local models with your OpenClaw …
Source: LM Studio (X) | 2026-09-19