← All machines
Apple unified memory · Apple
Apple Mac mini (M5 Pro, 20-core GPU)
The M5 Pro Mac mini with the larger GPU, configurable to 64GB. At 64GB it runs 30B-class models at 4-bit with room left for long context.
Memory for models
48 GBassumption
Assumed three quarters of 64 GB for macOS's default GPU limit, which Apple does not publish.
Memory bandwidth
307 GB/s
Maker price
~$1,899–$2,899
Largest at 4-bit
46.9 GB at 8,192 tokens of context, default GPU limit (an assumed limit, see Memory for models)
gpt-oss-20b, 4-bit
80 tok/smedian of 3 runs
Memory configurations
One page covers every memory option the maker sells. Prices are the maker’s list price for the cheapest configuration with that much memory.
| Memory | Price | Memory the GPU can use |
|---|---|---|
| 24 GB | ~$1,899 | 16 GB default gpu limitassumption 16 GB limit raised with sysctlassumption |
| 48 GB | ~$2,499 | 36 GB default gpu limitassumption 40 GB limit raised with sysctlassumption |
| 64 GB | ~$2,899 | 48 GB default gpu limitassumption 56 GB limit raised with sysctlassumption |
Assumed three quarters of 64 GB for macOS's default GPU limit, which Apple does not publish. Raised with iogpu.wired_limit_mb per the MLX docs, leaving an assumed 8 GB for macOS. How GPU memory limits work on unified-memory machines.
What it runs at 4-bit
Every model in the catalog at its 4-bit file with 8,192 tokens of context. 22 of 41 fit in at least one configuration. Speeds are the median of measured runs on the same chip where any exist; otherwise an estimate from memory bandwidth. Try other quants and context lengths.
| Model | Needs | Fit | Generation speed |
|---|---|---|---|
| Kimi K32.8T, 104B active · UD-Q4_K_XL | 1406.8 GBcontext memory estimated | Does not fit | |
| DeepSeek V4 Pro1.6T, 49B active · Q4_K_M | 890.5 GBcontext memory not counted | Does not fit | |
| Kimi K2.61T, 32B active · UD-Q4_K_XL | 545.7 GBcontext memory estimated | Does not fit | |
| DeepSeek V4.1 Flash552B, 16B active · Q4 (DwarfStar) | 484.5 GB | Does not fit | |
| GLM-5.3753.3B · UD-Q4_K_XL | 437.4 GBcontext memory estimated | Does not fit | |
| DeepSeek V3.2671B, 37B active · Q4_K_M | 379.6 GBcontext memory estimated | Does not fit | |
| MiniMax M3428B, 23B active · Q4_K_M | 244.8 GBcontext memory not counted | Does not fit | |
| Qwen3.5 397B-A17B397B, 17B active · Q4_K_M | 229.1 GBcontext memory estimated | Does not fit | |
| GLM-5.3 Flash320B, 18B active · UD-Q4_K_XL | 187.6 GBcontext memory estimated | Does not fit | |
| Hy3295B, 21B active · Q4_K_M | 173.6 GB | Does not fit | |
| MiniMax M2.7228.7B · Q4_K_M | 132.7 GB | Does not fit | |
| Qwen3.8 Flash-Next125B, 6B active · Q4_K_M | 113.1 GBcontext memory estimated | Does not fit | |
| Nemotron 3 Super 120B-A12B120B, 12B active · Q4_K_M | 82.6 GBcontext memory estimated | Does not fit | |
| Qwen3.5 122B-A10B122B, 10B active · Q4_K_M | 73.0 GBcontext memory estimated | Does not fit | |
| Mistral Medium 3.5 128B128B · Q4_K_M | 74.0 GB | Does not fit | |
| GLM-4.5-Air106B, 12B active · Q4_K_M | 70.9 GB | Does not fit | |
| Mistral Small 4 119B (2603)119B, 6.5B active · Q4_K_M | 69.3 GBcontext memory estimated | Does not fit | |
| Llama 4 Scout 17B-16E Instruct109B, 17B active · Q4_K_M | 62.4 GBcontext memory not counted | Does not fit | |
| gpt-oss-120b117B, 5.1B active · MXFP4 (native) | 60.2 GBcontext memory estimated | Does not fit | |
| Qwen3 Coder Next80B, 3B active · Q4_K_M | 46.9 GBcontext memory estimated | Fitsassumed limitfrom the 64 GB config | 74 tok/smedian of 2 runs |
| Llama 3.3 70B Instruct70B · Q4_K_M | 43.6 GB | Fitsassumed limitfrom the 64 GB config | 6.9 tok/smedian of 3 runs |
| Nemotron 3.5 Lightning 30B-A3B30B, 3B active · Q4_K_M | 25.3 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | 106 tok/smedian of 2 runs |
| Qwen3.6 35B-A3B35B, 3B active · Q4_K_M | 22.4 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | ~53–95 tok/sestimate |
| Ornith 1.5 35B-A3B35B, 3B active · Q4_K_M | 21.9 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | ~55–98 tok/sestimate |
| Qwen3 Coder 30B-A3B Instruct30.5B, 3.3B active · Q4_K_M | 19.5 GB | Fitsassumed limitfrom the 48 GB config | 95 tok/smedian of 1 run |
| Gemma 4 31B IT30.7B · Q4_K_M | 18.9 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | 13 tok/smedian of 3 runs |
| Granite 4.2 30B29.3B · Q4_K_M | 20.3 GB | Fitsassumed limitfrom the 48 GB config | ~13–16 tok/sestimate |
| Qwen3.8 27B27B · Q4_K_M | 18.2 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | 14 tok/smedian of 1 run |
| Gemma 4 26B-A4B IT25.2B, 3.8B active · Q4_K_M | 17.4 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | 71 tok/smedian of 2 runs |
| Qwen3.6 27B27B · Q4_K_M | 17.7 GBcontext memory estimated | Fitsassumed limitfrom the 48 GB config | 13 tok/smedian of 3 runs |
| Devstral Small 2 24B (2512)24B · Q4_K_M | 16.1 GB | Fitsassumed limitfrom the 48 GB config | ~16–20 tok/sestimate |
| gpt-oss-20b21B, 3.6B active · MXFP4 (native) | 12.5 GBcontext memory estimated | Fitsassumed limitfrom the 24 GB config | 80 tok/smedian of 3 runs |
| Phi-414.7B · Q4_K_M | 11.3 GB | Fitsassumed limitfrom the 24 GB config | ~25–32 tok/sestimate |
| Ministral 3 14B Reasoning (2512)13.9B · Q4_K_M | 10.4 GB | Fitsassumed limitfrom the 24 GB config | ~27–34 tok/sestimate |
| Gemma 4 12B IT11.95B · Q4_K_M | 8.2 GBcontext memory estimated | Fitsassumed limitfrom the 24 GB config | ~32–39 tok/sestimate |
| Qwen3.5 9B9B · Q4_K_M | 7.0 GBcontext memory estimated | Fitsassumed limitfrom the 24 GB config | 56 tok/smedian of 1 run |
| Granite 4.2 8B8.8B · Q4_K_M | 7.9 GB | Fitsassumed limitfrom the 24 GB config | ~41–51 tok/sestimate |
| Gemma 4 E4B IT8B · Q4_K_M | 6.5 GBcontext memory not counted | Fitsassumed limitfrom the 24 GB config | ~74–92 tok/sestimate |
| Qwen3 8B8.2B · Q4_K_M | 7.3 GB | Fitsassumed limitfrom the 24 GB config | ~45–56 tok/sestimate |
| Llama 3.1 8B Instruct8B · Q4_K_M | 7.1 GB | Fitsassumed limitfrom the 24 GB config | 45 tok/smedian of 1 run |
| Qwen3.5 4B4B · Q4_K_M | 4.3 GBcontext memory estimated | Fitsassumed limitfrom the 24 GB config | ~82–102 tok/sestimate |
Measured speeds
32 published runs with one user, plain decoding and at most 4,096 tokens already in context, on M5 Pro (18-core CPU, 20-core GPU).
| Model | Quant | Backend | Generation | Prompt | Context | Measured on | Source |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B-A4B IT | 4bit (MLX) | oMLX (version not stated) | 72 tok/s | 2,165 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 26B-A4B IT | 4bit (MLX) | oMLX (version not stated) | 71 tok/s | 2,463 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 26B-A4B IT | 8bit (MLX) | oMLX (version not stated) | 54 tok/s | 2,291 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 26B-A4B IT | 8bit (MLX) | oMLX (version not stated) | 54 tok/s | 2,288 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 4-bit MLX (gemma-4-31B-it-MLX-4bit) | oMLX (version not stated) (MLX) | 15 tok/s | 377 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 4bit (MLX) | oMLX (version not stated) | 13 tok/s | 389 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 4bit (MLX) | oMLX (version not stated) | 13 tok/s | 377 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| GLM-5.3 Flash | 4-bit MLX (GLM-5.3-Flash-oQ4e) | oMLX (version not stated) (MLX) | 1.0 tok/s | 16 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-09 |
| GLM-5.3 Flash | 4bit (MLX) | oMLX (version not stated) | 0.9 tok/s | 30 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-09 |
| gpt-oss-120b | 2bit (MLX) | oMLX (version not stated) | 72 tok/s | 997 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-05 |
| gpt-oss-20b | 4bit (MLX) | oMLX (version not stated) | 81 tok/s | 2,831 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| gpt-oss-20b | 4bit (MLX) | oMLX (version not stated) | 80 tok/s | 1,899 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| gpt-oss-20b | 4-bit MLX (gpt-oss-20b-MXFP4-Q8) | oMLX (version not stated) (MLX) | 65 tok/s | 1,982 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-10 |
| gpt-oss-20b | MXFP4 | llama.cpp master (2026-09-28) | – | 1,446 tok/s512-token prompt | 4,096 | a machine with the same chip | llama.cpp benchmark discussion2026-09 |
| Llama 3.1 8B Instruct | Q4_K_M | LocalScore (llamafile/llama.cpp, version not stated) | 45 tok/s | 411 tok/s | 0 | a machine with the same chip | LocalScore2026-10 |
| Llama 3.3 70B Instruct | 4-bit MLX (Llama-3.3-70B-Instruct) | oMLX (version not stated) (MLX) | 6.9 tok/s | 161 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-03 |
| Llama 3.3 70B Instruct | 4bit (MLX) | oMLX (version not stated) | 6.9 tok/s | 179 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Llama 3.3 70B Instruct | 4bit (MLX) | oMLX (version not stated) | 6.8 tok/s | 162 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Nemotron 3.5 Lightning 30B-A3B | 4bit (MLX) | oMLX (version not stated) | 106 tok/s | 2,014 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-09 |
| Nemotron 3.5 Lightning 30B-A3B | 4bit (MLX) | oMLX (version not stated) | 105 tok/s | 1,982 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-09 |
| Qwen3 Coder 30B-A3B Instruct | 4-bit MLX (Qwen3-Coder-30B-A3B-Instruct-4bit) | oMLX (version not stated) (MLX) | 95 tok/s | 2,352 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3 Coder Next | 4bit (MLX) | oMLX (version not stated) | 76 tok/s | 2,347 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3 Coder Next | 4bit (MLX) | oMLX (version not stated) | 72 tok/s | 2,283 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.5 122B-A10B | 4-bit MLX (Qwen3.5-122B-A10B-RAM-48GB) | oMLX (version not stated) (MLX) | 31 tok/s | 572 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-07 |
| Qwen3.5 9B | 4-bit MLX (Qwen3.5-9B-MLX-4bit) | oMLX (version not stated) (MLX) | 56 tok/s | 1,523 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 4bit (MLX) | oMLX (version not stated) | 18 tok/s | 487 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 4-bit MLX (Qwen3.6-27B-UD-Q4_K_XL-mlx) | oMLX (version not stated) (MLX) | 13 tok/s | 467 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 4bit (MLX) | oMLX (version not stated) | 11 tok/s | 240 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 6bit (MLX) | oMLX (version not stated) | 13 tok/s | 484 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 8bit (MLX) | oMLX (version not stated) | 6.1 tok/s | 212 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 27B | 4-bit MLX (Qwen3.8-27B-OptiQ-4bit) | oMLX (version not stated) (MLX) | 14 tok/s | 464 tok/s1,024-token prompt | 1,024 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 27B | Q8_0 | llama.cpp master (2026-09-28) | 9.2 tok/s | 383 tok/s512-token prompt | 0 | a machine with the same chip | llama.cpp benchmark discussion2026-09 |
With speculative decoding
A small draft model or extra prediction heads guess several tokens ahead. Generation is faster on text the guesses get right, so these are kept out of the medians above.
| Model | Quant | Backend | Generation | Prompt | Context | Measured on | Source |
|---|---|---|---|---|---|---|---|
| Gemma 4 26B-A4B IT | 8bit (MLX) | oMLX (version not stated) | 62 tok/s | 2,238 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 26B-A4B IT | 8bit (MLX) | oMLX (version not stated) | 29 tok/s | 975 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 4bit (MLX) | oMLX (version not stated) | 22 tok/s | 384 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 4bit (MLX) | oMLX (version not stated) | 15 tok/s | 509 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 8bit (MLX) | oMLX (version not stated) | 17 tok/s | 458 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Gemma 4 31B IT | 8bit (MLX) | oMLX (version not stated) | 12 tok/s | 471 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Nemotron 3.5 Lightning 30B-A3B | 4bit (MLX) | oMLX (version not stated) | 102 tok/s | 1,346 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 4bit (MLX) | oMLX (version not stated) | 32 tok/s | 480 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 35B-A3B | 4bit (MLX) | oMLX (version not stated) | 108 tok/s | 3,189 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 35B-A3B | 4bit (MLX) | oMLX (version not stated) | 103 tok/s | 1,962 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 35B-A3B | 8bit (MLX) | oMLX (version not stated) | 87 tok/s | 1,740 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 27B | 4bit (MLX) | oMLX (version not stated) | 34 tok/s | 502 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 27B | 4bit (MLX) | oMLX (version not stated) | 33 tok/s | 697 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 Flash-Next | 3bit (MLX) | oMLX (version not stated) | 20 tok/s | 280 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 Flash-Next | 3bit (MLX) | oMLX (version not stated) | 18 tok/s | 328 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 Flash-Next | 4bit (MLX) | oMLX (version not stated) | 37 tok/s | 842 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.8 Flash-Next | 4bit (MLX) | oMLX (version not stated) | 12 tok/s | 191 tok/s4,096-token prompt | 4,096 | a machine with the same chip | oMLX benchmark submission2026-10 |
Deep into a long context
Measured with more than 4,096 tokens already in context, where every new token also reads the context memory.
| Model | Quant | Backend | Generation | Prompt | Context | Measured on | Source |
|---|---|---|---|---|---|---|---|
| Gemma 4 31B IT | 4-bit MLX (gemma-4-31b-it-4bit) | oMLX (version not stated) (MLX) | 11 tok/s | 331 tok/s16,384-token prompt | 16,384 | a machine with the same chip | oMLX benchmark submission2026-10 |
| gpt-oss-20b | 4-bit MLX (gpt-oss-20b-MXFP4-Q8) | oMLX (version not stated) (MLX) | 69 tok/s | 2,565 tok/s16,384-token prompt | 16,384 | a machine with the same chip | oMLX benchmark submission2026-10 |
| gpt-oss-20b | 4-bit MLX (gpt-oss-20b-MXFP4-Q8) | oMLX (version not stated) (MLX) | 55 tok/s | 1,917 tok/s32,768-token prompt | 32,768 | a machine with the same chip | oMLX benchmark submission2026-09 |
| Llama 3.1 8B Instruct | Q4_K_M | llama.cpp master (2026-10-16) | 43 tok/s | – | 8,192 | a machine with the same chip | llama.cpp benchmark discussion2026-10 |
| Llama 3.1 8B Instruct | Q4_K_M | llama.cpp master (2026-10-16) | 28 tok/s | – | 32,768 | a machine with the same chip | llama.cpp benchmark discussion2026-10 |
| Qwen3 Coder 30B-A3B Instruct | 4-bit MLX (Qwen3-Coder-30B-A3B-Instruct-4bit) | oMLX (version not stated) (MLX) | 55 tok/s | 1,709 tok/s16,384-token prompt | 16,384 | a machine with the same chip | oMLX benchmark submission2026-09 |
| Qwen3 Coder 30B-A3B Instruct | 4-bit MLX (Qwen3-Coder-30B-A3B-Instruct) | oMLX (version not stated) (MLX) | 40 tok/s | 1,099 tok/s32,768-token prompt | 32,768 | a machine with the same chip | oMLX benchmark submission2026-07 |
| Qwen3.5 9B | 4-bit MLX (Qwen3.5-9B-4bit) | oMLX (version not stated) (MLX) | 52 tok/s | 1,759 tok/s16,384-token prompt | 16,384 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.5 9B | 4-bit MLX (Qwen3.5-9B-MLX-4bit) | oMLX (version not stated) (MLX) | 45 tok/s | 1,579 tok/s32,768-token prompt | 32,768 | a machine with the same chip | oMLX benchmark submission2026-10 |
| Qwen3.6 27B | 4-bit MLX (Qwen3.6-27B-4bit) | oMLX (version not stated) (MLX) | 16 tok/s | 386 tok/s32,768-token prompt | 32,768 | a machine with the same chip | oMLX benchmark submission2026-08 |
| Qwen3.6 27B | 4-bit MLX (Qwen3.6-27B-4bit) | oMLX (version not stated) (MLX) | 13 tok/s | 306 tok/s16,384-token prompt | 16,384 | a machine with the same chip | oMLX benchmark submission2026-08 |
| Qwen3.8 27B | Q8_0 | llama.cpp master (2026-10-16) | 9.2 tok/s | – | 8,192 | a machine with the same chip | llama.cpp benchmark discussion2026-10 |
| Qwen3.8 27B | Q8_0 | llama.cpp master (2026-10-14) | 9.1 tok/s | 324 tok/s512-token prompt | 8,192 | a machine with the same chip | llama.cpp benchmark discussion2026-10 |
| Qwen3.8 27B | Q8_0 | llama.cpp master (2026-10-16) | 8.4 tok/s | – | 32,768 | a machine with the same chip | llama.cpp benchmark discussion2026-10 |
| Qwen3.8 27B | Q8_0 | llama.cpp master (2026-09-28) | – | 296 tok/s512-token prompt | 8,192 | a machine with the same chip | llama.cpp benchmark discussion2026-09 |
| Qwen3.8 27B | Q8_0 | llama.cpp master (2026-09-28) | – | 174 tok/s512-token prompt | 32,768 | a machine with the same chip | llama.cpp benchmark discussion2026-09 |
Specifications
- Chip
- M5 Pro (18-core CPU, 20-core GPU)
- Memory
- unified LPDDR (Apple does not state the generation)
- Memory bandwidth
- 307 GB/s
- FP16 compute
- Apple does not publish TFLOPS for the M5 Pro GPU or its Neural Accelerators
- Software
- Metal, MLX
- Ships with
- macOS
- Power
- 155 W (Maximum continuous power, Apple tech specs)
- Form factor
- Mini PC
- Networking
- 2.5GbE (10GbE option); three Thunderbolt 5, which Apple says can cluster multiple Mac minis
- Released
- 2026-09
- Maker page
- apple.com
Sources
- apple.com: M5 Pro chip, 307GB/s, memory options, 155W max continuous power, ports
- apple.com: base prices $1,699 (15-core) and $1,899 (18-core)
- apple.com: Thunderbolt 5 clustering, 2.5GbE
- apple.com: available 2026-09-22
- apple.com: memory deltas: 24GB +$0, 48GB +$600, 64GB +$1,000 over $1,899
- github.com: how far the GPU memory limit can be raised on a Mac (sysctl iogpu.wired_limit_mb)
- github.com: the default GPU memory limit on a Mac and how to raise it
Compared with
Similar machines
- Apple Mac mini (M5 Pro, 16-core GPU)~$1,699–$2,699
- Apple Mac Studio (M5 Max, 32-core GPU)~$2,499
- Apple Mac Studio (M5 Max, 40-core GPU)~$3,099–$5,099