maruhana·10h agoA 120B Model Ran About 4× Faster Than a 27B One: 8 Local LLMs on a Surface Laptop UltraSame llama.cpp build, same commands, one Surface Laptop Ultra (Windows on Arm, RTX Spark): generation speed lined up by active parameters…
InTowards AIbyAnkit Agrawal·10h agoWhich Uncensored Qwen Quant to Run On Your Mac: 16GB to 128GB Picks (2026)One abliterated Qwen GGUF per Mac RAM size (9B, 27B or Flash-Next), with Hugging Face file sizes and the context each leaves room for.A response icon1A response icon1
Dhirendra Choudhary·16h agoI Gave a 2.7 GB Model 10 Three.js Prompts. 3 WorkedQwen3.5–4B-3D-Coder against a 17 GB coding model on the same ten scenes, on one MacBook. The specialist loses, narrowly
InDev GeniusbyDiko Ko·1d agoBuying the New M5 Ultra Mac Studio with 512 GB of MemoryIn February, I wrote about running OpenCode with local LLMs on my M3 Ultra Mac Studio. It became one of my most-read posts on Medium. In a…
Vishal·1d agoThe Best Local LLM for Your Mac in 2026 Isn’t the Smartest One. It’s the One That Fits .Most people pick a local model the way they pick a phone: by the leaderboard.A response icon1A response icon1
Agent Native·2d agoLocal Inference Engine That Makes Agents Faster on MacLocal models have improved enough to handle useful development work.
Dhirendra Choudhary·3d agoHow Good Are Local LLMs Now? The “Good Enough” FrontierI gave the 20-month-old model on my MacBook 14 graded tasks in early October 2026. It handled the boring 80%, and failed the 20% in a way I…
Sajith K·3d agoSame Model, Same Laptop, Four Times FasterQwen3.8–27B on a fanless 24 GB M5 MacBook Air: llama.cpp versus uzu, measured on real agentic coding tasks rather than a tokens-per-second…A response icon1A response icon1
Maks Khomutskyi·3d agoMy $1,043 AMD AI Box vs. a DeepSeek API Run for Under 19 CentsSix playable tower-defense games: my Ryzen AI 9 HX 370 PC vs. DeepSeek API, using Pi, Strata and Graphify. Results and estimated costs.
InProfit4Cloud — AIbyIddo Kerkhof·3d agoWhy Use Local LLMs After Fable 5.2?When Local LLMs Are the Right Tool for the Job
