Qwen3.5-4B running CPU-ONLY at up to ~11+ tps on a Ryzen 5 laptop. No GPU. Running models in RAM and CPU is something the Qwen4 team is already thinking about. 💡 I built this standalone .exe because businesses are already deploying local models to save money and ensure privacy. (thumb drive friendly - just drag drop and doubleclick) My llama.cpp recipe 👉 🧠 Qwen3.5-4B Q4_K_M GGUF ⚙️ Ryzen 5 7540U — 6C/12T 🧵 --threads 9 🧵 --threads-batch 12 ⚡ --prio 2 🔄 --poll 50 📦 --batch-size 2048 📦 --ubatch-size 512 🚀 --flash-attn on 🧠 KV cache: q4_0 / q4_0 🔧 --repack 💾 --mmap 👤 --parallel 1 🚫 --device none 🚫 --gpu-layers 0 🚫 KV/op GPU offload 🚫 MTP OFF Interesting result 👉 MTP=3 was slower (~10 tps in benchmarks). Plain decode + 9 threads + Q4 KV hit ~11.4 tok/s. That's about 10% faster just from tuning llama.cpp — on a basic laptop CPU.

Someone filming from a high-rise in Boston spots this insane rooftop setup and is straight up mindblown “Is this even a house? Who lives here? What is this?” Turns out it’s a full-on luxury penthouse duplex built right on top of the buildings at 326 A St STE 6C, Melcher Street, Fort Point It’s a real 4,383 sq ft home (sold for $3.6M recently) that genuinely looks like a standalone house sitting on the roof That looks unbelievably cool

Leadoff Double #6# @CoachHannahs @CoachReif @32JonnyA @CoachEddieSmith @RobFournierWKU @CoachSimmons4 @k_hunt11 @hardy03bsbl @VanderhookCory @Gierke12 @earleybaseball @PuccioNick @JackMarder14 @T_Rost12 @CoachMikeBianco @RudyCox_6 @c_breezy2 @CoachWazUO @Ejmccummings12 @DWoo22