Topic · ai
Local AI
Running models inside a client's own network: data residency, on-prem GPUs and the architecture that makes it viable.
Notes
6 published
006Ternary Bonsai 2 27B: Qwen3.8-27B in 5.9GB, and where the 98% stopsPrismML released Ternary Bonsai 2 27B on 17 September 2026, a ternary-weight build of Qwen3.8-27B that fits in 5.9GB and keeps 98.2% of the full model's benchmark average. On long-horizon agent tasks it keeps about three quarters. Here is how to read both numbers before you replace a 4-bit quant.TECH NOTE · 8 MIN005A 27B model under Apache 2.0: what Qwen3.8-27B changes for local AIAlibaba published Qwen3.8-27B weights on 14 August 2026 under Apache 2.0, dense rather than mixture-of-experts, with a 262k native context. The licence matters more than the benchmark scores, and here is why.AI NOTE · 6 MIN004Saudi Arabia is an interesting place to build enterprise AINot for the reasons usually given. The interesting parts are the constraints - data that will not move, Arabic as a first-class requirement, and buyers who ask hard questions early.OPINION · 3 MIN003The best architecture is sometimes hybrid: local + cloud AIHybrid is usually the right answer and usually implemented badly - arrived at by accident rather than designed, which gives you the costs of both and the clarity of neither.SYSTEM NOTE · 2 MIN002Local AI vs cloud AI: what actually makes sense for Saudi companies?The comparison usually gets made on price, which is the least interesting axis. Here is how the decision actually breaks down, including when the honest answer is cloud.AI NOTE · 4 MIN001Why I'm interested in Mac minis for local AI deploymentsA small machine on a shelf is a genuinely viable AI deployment target now. Here is what that is good for, and the parts people leave out.BUILD LOG · 3 MIN