Blog

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

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.

Nov 4, 2026Mac mini M6Mac mini serverM5 ProMac mini M6 serverhome serverlocal LLMlocal AIMLXllama.cppOllamaself-hostingMac mini M6 vs M5 Pro

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.

Nov 4, 2026free ChatGPT alternativeChatGPT free planlocal AIlocal LLMQwenQwen3.8RTX 3090RTX 5090Mac mini M624GB GPUquantizationllama.cpp

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).

Nov 4, 2026StrataStrata enginestrata-mlxMac mini M6Mac mini 32GBQwen3.8Flash-NextQwen 27Blocal LLMKMMLUllama.cpp2-bit quantization

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).

Nov 4, 2026Mac mini M6Mac mini 32GBQwen3.8Qwen 27B4-bit quantizationspeculative decodingDFlash2MTPllama.cppMLXlocal LLMKorean tokens per second