Mac Studio, M5 Max, 64GB

512GB of storage, 614GB/s of memory bandwidth, and 59GB of unified memory left for a model once macOS has taken its share. It holds 17 of the 30 models we track.

Offers

checked 45 days ago

Applelist pricecheapest todayin stockchecked 45 days ago$3,499

Timing

Collecting price history — 0 of 90 days. No timing verdict yet.

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-16EQ3_K_M
Tight3GB headroomest. 36.9 tok/s
Qwen3-Coder-NextQ5_K_M
Tight1GB headroomest. 144 tok/s
Llama-3.3-70BQ5_K_M
Fits5GB headroomest. 8.0 tok/s
Qwen3.5-35B-A3BQ8_0
Fits20GB headroomest. 96.3 tok/s
Qwen3-32BQ8_0
Fits22GB headroomest. 11.7 tok/s
Gemma-4-31BQ8_0
Fits24GB headroomest. 12.2 tok/s
Qwen3-30B-A3BQ8_0
Fits24GB headroomest. 87.6 tok/s
Gemma-3-27BBF16
Tight2GB headroomest. 7.4 tok/s
Qwen3.6-27BBF16
Tight3GB headroomest. 7.4 tok/s
Gemma-4-26B-A4BBF16
Fits7GB headroomest. 40.4 tok/s
Devstral-Small-2507BF16
Fits8GB headroomest. 8.3 tok/s
gpt-oss-20bBF16
Fits15GB headroomest. 42.6 tok/s
Phi-4BF16
Fits28GB headroomest. 14.3 tok/s
Gemma-4-12BBF16
Fits33GB headroomest. 16.7 tok/s
Qwen3-VL-8B-InstructBF16
Fits41GB headroomest. 24.9 tok/s
Gemma-3n-E4BBF16
Fits44GB headroomest. 49.9 tok/s
Qwen3-4BBF16
Fits49GB headroomest. 49.9 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	Q3_K_M	Tight	3GB	36.9 tok/s
Qwen3-Coder-Next	Q5_K_M	Tight	1GB	144 tok/s
Llama-3.3-70B	Q5_K_M	Fits	5GB	8.0 tok/s
Qwen3.5-35B-A3B	Q8_0	Fits	20GB	96.3 tok/s
Qwen3-32B	Q8_0	Fits	22GB	11.7 tok/s
Gemma-4-31B	Q8_0	Fits	24GB	12.2 tok/s
Qwen3-30B-A3B	Q8_0	Fits	24GB	87.6 tok/s
Gemma-3-27B	BF16	Tight	2GB	7.4 tok/s
Qwen3.6-27B	BF16	Tight	3GB	7.4 tok/s
Gemma-4-26B-A4B	BF16	Fits	7GB	40.4 tok/s
Devstral-Small-2507	BF16	Fits	8GB	8.3 tok/s
gpt-oss-20b	BF16	Fits	15GB	42.6 tok/s
Phi-4	BF16	Fits	28GB	14.3 tok/s
Gemma-4-12B	BF16	Fits	33GB	16.7 tok/s
Qwen3-VL-8B-Instruct	BF16	Fits	41GB	24.9 tok/s
Gemma-3n-E4B	BF16	Fits	44GB	49.9 tok/s
Qwen3-4B	BF16	Fits	49GB	49.9 tok/s

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