Blog
Written versions of our YouTube videos, so you can check the numbers and tables at your own pace.
Mac Studio M5 Max 128GB vs M5 Ultra 96GB: Which for Local AI?
Mac Studio M5 Max 128GB vs M5 Ultra 96GB for local AI: Ultra for speed at 27B and under, Max for 122B-class MoE. Measured and estimated numbers kept apart.
Mac mini M6 32GB Server vs M5 Pro 24GB: 5 Use Cases (M6 Measured)
Mac mini M6 32GB vs M5 Pro 24GB as a server in 5 cases: website, home server, small AI, multi-user AI, big models. M6 measured, M5 Pro from public data.
Free ChatGPT-Class Local AI on a 24GB GPU? RTX 3090, 5090, Mac mini
Can one 24GB GPU (RTX 3090, 4-bit) get into the same league as free ChatGPT? We ran the same questions on a 3090, 5090 and Mac mini M6 and compared memory, speed and quality.
Mac mini M6 16GB vs 24GB vs 32GB: Which to Buy? 8 Uses Tested
Which Mac mini M6 to buy, 16GB, 24GB or 32GB? We measured 8 uses on a 32GB unit. 24GB and 16GB are simulated, local AI is estimated. The split is model size.
DGX Spark Tested: 128GB Boxes vs Mac mini M6 (as of Sept 2026)
We rented a DGX Spark and ran the same models as a Mac mini M6 32GB. One user: Mac mini (64 vs 40 tokens/s). 16 users: DGX Spark (319 vs 166). As of 2026-09.
Strata on Mac mini 32GB: 10.3-22.1 Tokens/s (Thinking On) vs 27B
Strata on a Mac mini M6 32GB runs Qwen3.8 Flash-Next Q2_0 (66.4GB) at 10.3-22.1 tokens/s (thinking-on format). No accuracy difference confirmed vs 27B 4-bit (150 questions, 52 coding problems).
Qwen3.8 27B 4-bit on Mac mini M6 32GB: 49.7 Tokens/s JSON, 8.8 Korean
Qwen3.8 27B 4-bit on a Mac mini M6 32GB: the fastest combo hits 49.7 tokens/s on JSON but only 8.8 on Korean, and the fastest file loses the most quality (vs UD-Q6_K).