Mac mini, M5 Pro, 48GB

512GB of storage, 307GB/s of memory bandwidth, and 44GB of unified memory left for a model once macOS has taken its share. It holds 16 of the 30 models we track.

Offers

checked 43 minutes ago

Applelist pricecheapest todayin stockchecked 43 minutes ago$2,499

Timing

Buy now. $2,499 is the lowest price in 46 days.

Models it runs — 8K context

Llama-4-Behemoth—
Won't fit— headroom
DeepSeek-V4-Pro—
Won't fit— headroom
Kimi-K2-Instruct—
Won't fit— headroom
DeepSeek-V3—
Won't fit— headroom
DeepSeek-R1—
Won't fit— headroom
Qwen3-Coder-480B-A35B-Instruct—
Won't fit— headroom
Llama-4-Maverick-17B-128E—
Won't fit— headroom
GLM-4.6—
Won't fit— headroom
DeepSeek-V4-Flash—
Won't fit— headroom
Qwen3-235B-A22B—
Won't fit— headroom
MiniMax-M2—
Won't fit— headroom
Mistral-Large-2411—
Won't fit— headroom
gpt-oss-120b—
Won't fit— headroom
Llama-4-Scout-17B-16E—
Won't fit— headroom
Qwen3-Coder-NextQ3_K_M
Tight4GB headroomest. 105 tok/s
Llama-3.3-70BQ3_K_M
Fits6GB headroomest. 5.8 tok/s
Qwen3.5-35B-A3BQ8_0
Fits6GB headroomest. 48.2 tok/s
Qwen3-32BQ8_0
Fits7GB headroomest. 5.9 tok/s
Gemma-4-31BQ8_0
Fits9GB headroomest. 6.1 tok/s
Qwen3-30B-A3BQ8_0
Fits10GB headroomest. 43.8 tok/s
Gemma-3-27BQ8_0
Fits12GB headroomest. 7.0 tok/s
Qwen3.6-27BQ8_0
Fits14GB headroomest. 7.0 tok/s
Gemma-4-26B-A4BQ8_0
Fits16GB headroomest. 38.0 tok/s
Devstral-Small-2507Q8_0
Fits16GB headroomest. 7.8 tok/s
gpt-oss-20bBF16
Tight1GB headroomest. 21.3 tok/s
Phi-4BF16
Fits13GB headroomest. 7.1 tok/s
Gemma-4-12BBF16
Fits19GB headroomest. 8.3 tok/s
Qwen3-VL-8B-InstructBF16
Fits26GB headroomest. 12.5 tok/s
Gemma-3n-E4BBF16
Fits29GB headroomest. 24.9 tok/s
Qwen3-4BBF16
Fits34GB headroomest. 24.9 tok/s

Model	Best quant	Fit	Headroom	Est. speed
Llama-4-Behemoth	—	Won't fit	—	—
DeepSeek-V4-Pro	—	Won't fit	—	—
Kimi-K2-Instruct	—	Won't fit	—	—
DeepSeek-V3	—	Won't fit	—	—
DeepSeek-R1	—	Won't fit	—	—
Qwen3-Coder-480B-A35B-Instruct	—	Won't fit	—	—
Llama-4-Maverick-17B-128E	—	Won't fit	—	—
GLM-4.6	—	Won't fit	—	—
DeepSeek-V4-Flash	—	Won't fit	—	—
Qwen3-235B-A22B	—	Won't fit	—	—
MiniMax-M2	—	Won't fit	—	—
Mistral-Large-2411	—	Won't fit	—	—
gpt-oss-120b	—	Won't fit	—	—
Llama-4-Scout-17B-16E	—	Won't fit	—	—
Qwen3-Coder-Next	Q3_K_M	Tight	4GB	105 tok/s
Llama-3.3-70B	Q3_K_M	Fits	6GB	5.8 tok/s
Qwen3.5-35B-A3B	Q8_0	Fits	6GB	48.2 tok/s
Qwen3-32B	Q8_0	Fits	7GB	5.9 tok/s
Gemma-4-31B	Q8_0	Fits	9GB	6.1 tok/s
Qwen3-30B-A3B	Q8_0	Fits	10GB	43.8 tok/s
Gemma-3-27B	Q8_0	Fits	12GB	7.0 tok/s
Qwen3.6-27B	Q8_0	Fits	14GB	7.0 tok/s
Gemma-4-26B-A4B	Q8_0	Fits	16GB	38.0 tok/s
Devstral-Small-2507	Q8_0	Fits	16GB	7.8 tok/s
gpt-oss-20b	BF16	Tight	1GB	21.3 tok/s
Phi-4	BF16	Fits	13GB	7.1 tok/s
Gemma-4-12B	BF16	Fits	19GB	8.3 tok/s
Qwen3-VL-8B-Instruct	BF16	Fits	26GB	12.5 tok/s
Gemma-3n-E4B	BF16	Fits	29GB	24.9 tok/s
Qwen3-4B	BF16	Fits	34GB	24.9 tok/s

Best quant is the highest-quality one that still loads with headroom. Every speed is an estimate; the formula is here.