Filter All Philosophy Fringe Tech Rant Essay Things I Love
AbliteratedOutTheBox: A llama.cpp Fork That Abliterates Per Prompt and Leaves the Weights Alone
A look-ahead gate, two directions read from the prompt, and a second prefill. One recipe for 131 llama.cpp architectures, with stock output on prompts the gate leaves alone.
3 min read
Strata vs oMLX: Qwen3.8-Flash-Next Decodes About 25% Faster at Long Context on a 128GB Mac
A one-month-old engine built for one model holds 74 tok/s at 245K context where oMLX holds 57.5, on the same 128GB M5 Max. The catch: one request at a time on Metal, for now.
5 min read
Qwen3.8-Flash-Next at 60 Tokens per Second Across Its Full 262K Context on a 128GB MacBook
oMLX with the MTP head and the n-gram table on SSD holds about 60 tok/s from empty to 245K; llama.cpp with MTP runs 59 fresh and 46 at 245K. Full window, vision on, identical output.
8 min read
The Cheapest 128 GB NVIDIA Box You Can Buy Right Now Is a Dell
Dell Pro Max with GB10 at about $5,523 versus the $6,950 DGX Spark, Strix Halo, Mac Studio M5, and used 3090s. Plus what a two-box pair really does.
12 min read