How to Run Bonsai 2 9B: GGUF Formats and Memory
Bonsai 2 9B’s default GGUF is 2.42GB; adding its Q8 vision projector brings downloads to 3.04GB. Match PQ2, PTQ or Q2 files to the correct llama.cpp build.
Jaxson Reed Editorial profile
EyesTech Local Model Usability Desk, focusing on consumer hardware quantization, on-device GGUF execution, and edge homelab deployments. Editorial Standards: https://eyestech.in/editorial-policy/
Liquid AI LFM2.5-24B: 2B Active MoE on Apple M5 Max
Liquid AI claims 184 tok/s on Apple M5 Max with 2.45B active compute, but LFM2.5-24B requires 15GB RAM, crushing 16GB laptops and lagging on SWE-bench.
How to Install and Run MiniCPM-V 4.7 1B in Ollama (Setup Guide)
MiniCPM-V 4.7 1B needs a 672 MB language file plus a 1.11 GB vision projector. Get the Ollama tag, llama.cpp recipe and visual-compression settings.
MiniCPM-V 4.7 Tested: System Requirements, VRAM & Local Setup Guide
MiniCPM-V 4.7 reports 13+ tokens/s in 3GB phone memory. Expert loading, quantization and speculation explain why that is not its total weight size.
Saluki 27B: What the 7.89GB Tool-Calling Win Hides
Saluki packs Qwen3.8-27B into 7.89GB. Its 88/120 tool score hides lost and gained tasks, parser sensitivity and memory costs beyond the model file.
How to Run 125B MoE Models on a 12GB GPU with Strata (Setup Guide)
Strata runs 125B Qwen3.8-Flash-Next on 12GB VRAM at 45 tok/s using predictive expert prefetching and io_uring. Here is the PCIe math and setup.
Surface Laptop Ultra & RTX Spark: 1 PFLOPS Grace+Blackwell SoC for 120B Local Agents
Microsoft and NVIDIA’s Surface Laptop Ultra pairs an Arm Grace CPU and Blackwell GPU via 300 GB/s NVLink-C2C. Here is what 128GB unified memory and 1 PFLOPS FP4 mean for 120B local agents.
Janus Brings Vulkan GGUF Inference to AMD and Intel GPUs Without Python or Docker
Janus bundles llama.cpp Vulkan DLLs into a 50MB Go binary for cross-vendor GGUF local LLM inference across AMD, Intel, and Nvidia GPUs without Python or Docker.
Backblaze Q2 2026: What a 1.73% Failure Rate Means
Backblaze reports 1.73% annualized failures for Q2 2026. Drive-days, fleet age and sample size explain why that figure is not a home-NAS forecast.
Xing4.0-29B-A4B: Why 4B Active Still Needs 18GB
China Telecom’s Xing4.0-29B-A4B activates about 4 billion parameters for each token, but it stores 29 billion parameters in total. That…