Blog
Running AI on your own machines: new models and what they need, the runtimes behind them, real tokens-per-second numbers, and coding agents on your own hardware.
Coding agents
Qwen3.8-27B pi adapter: what the coding-agent scores show
A new LoRA tunes Qwen3.8-27B for the Pi coding agent. What its scores show and miss, the files you need, and the two settings that matter.
New models
Run Ripple-65B locally: memory, speed and the benchmark gap
Ripple-65B Preview on your own hardware: real download sizes, the first DGX Spark speed figure, llama.cpp and Ollama support, and its disputed scores.
AI news
Edge0-145B: a 145B model on one 24GB GPU, with catches
Edge0-145B claims a 145B model on one 24GB card or a Mac. What it really needs (a 106 GB download, its own engine) and the licence catch.
Runtimes
llama.cpp 1.0: what changes if you run llama-server
llama.cpp 1.0 is out: a stricter llama-server on your network, an FP8 KV cache option, and removed flags to check before you upgrade.
AI news
MiniMax H3 Image in ComfyUI: file sizes and licence catch
MiniMax H3 Image runs in ComfyUI 0.45.0. What the local files weigh, what the templates need, and why its licence excludes the US, EU, UK and Korea.
Runtimes
Qwen3.8 Flash Next in Ollama: 27 GiB less memory on Macs
Ollama 0.40.16 cuts Qwen3.8 Flash Next memory on Apple silicon by about 27 GiB, aimed at 128GB Macs. What changed, what is unmeasured, how to run it.
New models
Best local LLM by memory: what fits in 16GB to 512GB
The strongest open model that fits at 16, 24, 32, 64, 128, 256 and 512GB of VRAM or unified memory, with real download sizes and sourced speeds.
Performance
Mac Studio for local LLMs: which M5 configuration to buy
The M5 Max and M5 Ultra Mac Studio for local LLMs: memory tiers, what Apple measured, which models fit, and how to use it from your laptop.