Blog
Written versions of our YouTube videos, so you can check the numbers and tables at your own pace.
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.
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).