Mac mini
Mac mini M5 Pro
15-core CPU / 16-core GPU, 24GB
24 GB of Unified memory at 307 GB/s. Runs up to GPT-OSS 20B, Gemma 4 12B, Qwen3.5 9B.
- Memory
- 24 GB ~17 GB usable for models
- Bandwidth
- 307 GB/s sets tokens/sec
- Software
- MLX MLX / Metal
- Price per GB
- $70.79 of model memory
Configurable to 48GB/64GB (price not captured). Base Mac mini (M6, 16GB, 153GB/s) is $899.
Where to buy
- Apple Store $1,699AvailableCheck price at Apple
What it runs
Estimated fit and decode speed for one user at ~8K context. How we estimate
- Qwen3.5 9Bdense · 9B active
Q4_K_MFits~34 tok/s7 of 17 GBQ8_0Fits~19 tok/s12 of 17 GB
- Gemma 4 12Bdense · 12B active
Q4_K_MFits~25 tok/s9 of 17 GBQ8_0Fits~14 tok/s15 of 17 GB
- GPT-OSS 20BMoE · 3.6B active
MXFP4 (native)Fits~96 tok/s13 of 17 GBQ8_0Won't fitneeds ~25 GB
- Gemma 4 26B-A4BMoE · 3.8B active
Q4_K_MWon't fitneeds ~18 GBQ8_0Won't fitneeds ~30 GB
- Qwen3.8 27Bdense · 27B active
Q4_K_MWon't fitneeds ~19 GBQ8_0Won't fitneeds ~32 GB
- GLM-4.7-Flash 30B-A3BMoE · 3B active
Q4_K_MWon't fitneeds ~21 GBQ8_0Won't fitneeds ~35 GB
- Gemma 4 31Bdense · 31B active
Q4_K_MWon't fitneeds ~21 GBQ8_0Won't fitneeds ~36 GB
- Qwen3.6 35B-A3BMoE · 3B active
Q4_K_MWon't fitneeds ~24 GBQ8_0Won't fitneeds ~41 GB
- Llama 3.3 70Bdense · 70B active
Q4_K_MWon't fitneeds ~46 GBQ8_0Won't fitneeds ~80 GB
- Qwen3-Next 80B-A3BMoE · 3B active
Q4_K_MWon't fitneeds ~52 GBQ8_0Won't fitneeds ~91 GB
- Llama 4 Scout 109B-A17BMoE · 17B active
Q4_K_MWon't fitneeds ~71 GBQ8_0Won't fitneeds ~123 GB
- GPT-OSS 120BMoE · 5.1B active
MXFP4 (native)Won't fitneeds ~67 GBQ8_0Won't fitneeds ~132 GB
- Nemotron 3 Super 120B-A12BMoE · 12B active
Q4_K_MWon't fitneeds ~78 GBQ8_0Won't fitneeds ~135 GB
- Qwen3.5 122B-A10BMoE · 10B active
Q4_K_MWon't fitneeds ~79 GBQ8_0Won't fitneeds ~138 GB
- Qwen3 235B-A22BMoE · 22B active
Q4_K_MWon't fitneeds ~151 GBQ8_0Won't fitneeds ~264 GB
- Muse Spark Open 816B-A42BMoE · 42B active
Q4_K_MWon't fitneeds ~521 GBQ8_0Won't fitneeds ~912 GB
Image: Apple Store product image