Mac mini, M6, 32GB vs Mac mini, M5 Pro, 24GB
Both hold Gemma-3-27B at Q4_K_M. Mac mini, M5 Pro, 24GB decodes an est. 12.2 tok/s against 6.8, and costs $200 more — $36.61.14542391914529 per extra token per second. Worth it if you read the output as it arrives; not if you queue jobs.
- Fit
- Fits
- Tight
- Headroom
- 9GB
- 1GB
- Est. speed
- 6.8 tok/s
- 12.2 tok/s
- Cheapest today
- $1,499 at Apple
- $1,699 at Apple
- Per GB of memory
- $47
- $71
- Memory
- 32GB unified memory
- 24GB unified memory
- Usable for a model
- 29GB
- 21GB
- Memory bandwidth
- 170GB/s
- 307GB/s
- Storage
- 512GB
- 512GB
- Lowest recorded
- $1,499 in 2d
- $1,699 in 2d
Fit, headroom and speed are computed from each vendor’s published bandwidth and the model’s own size at 8K context. Prices are the cheapest listing we could read on each seller’s page. The arithmetic is here.
Where they actually differ
- Qwen3-235B-A22BWon't fitWon't fit
- DeepSeek-V3Won't fitWon't fit
- Llama-3.3-70BWon't fitWon't fit
- gpt-oss-120bWon't fitWon't fit
- Mistral-Large-2411Won't fitWon't fit
- Llama-4-Scout-17B-16EWon't fitWon't fit
- Qwen3-32BFitsWon't fit
- Gemma-3-27BFitsTight
- gpt-oss-20bFitsFits
- Llama-4-Maverick-17B-128EWon't fitWon't fit
- Llama-4-BehemothWon't fitWon't fit
Every model we track at Q4_K_M. The rows where the two boxes agree are dimmed, because they are not what you are choosing between.