Mac Studio, M5 Max, 128GB

512GB of storage, 614GB/s of memory bandwidth, and 120GB of unified memory left for a model once macOS has taken its share. It holds 21 of the 30 models we track.

Offers

checked 43 minutes ago

Applelist pricecheapest todayin stockchecked 43 minutes ago$5,099
B&H Photonot availablechecked 45 days ago$5,099
Preorder, ships about 22 Sep.

No reseller undercuts Apple on this Config, so Apple direct is the price to beat.

Timing

Buy now. $5,099 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-A22BQ3_K_M
Tight2GB headroomest. 28.6 tok/s
MiniMax-M2Q3_K_M
Tight5GB headroomest. 62.8 tok/s
Mistral-Large-2411Q6_K
Fits15GB headroomest. 4.0 tok/s
gpt-oss-120bQ6_K
Fits22GB headroomest. 73.4 tok/s
Llama-4-Scout-17B-16EQ8_0
Tight1GB headroomest. 17.0 tok/s
Qwen3-Coder-NextQ8_0
Fits34GB headroomest. 96.3 tok/s
Llama-3.3-70BQ8_0
Fits42GB headroomest. 5.4 tok/s
Qwen3.5-35B-A3BBF16
Fits49GB headroomest. 51.2 tok/s
Qwen3-32BBF16
Fits53GB headroomest. 6.2 tok/s
Gemma-4-31BBF16
Fits56GB headroomest. 6.5 tok/s
Qwen3-30B-A3BBF16
Fits57GB headroomest. 46.5 tok/s
Gemma-3-27BBF16
Fits63GB headroomest. 7.4 tok/s
Qwen3.6-27BBF16
Fits64GB headroomest. 7.4 tok/s
Gemma-4-26B-A4BBF16
Fits68GB headroomest. 40.4 tok/s
Devstral-Small-2507BF16
Fits69GB headroomest. 8.3 tok/s
gpt-oss-20bBF16
Fits76GB headroomest. 42.6 tok/s
Phi-4BF16
Fits89GB headroomest. 14.3 tok/s
Gemma-4-12BBF16
Fits94GB headroomest. 16.7 tok/s
Qwen3-VL-8B-InstructBF16
Fits102GB headroomest. 24.9 tok/s
Gemma-3n-E4BBF16
Fits105GB headroomest. 49.9 tok/s
Qwen3-4BBF16
Fits110GB 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	Q3_K_M	Tight	2GB	28.6 tok/s
MiniMax-M2	Q3_K_M	Tight	5GB	62.8 tok/s
Mistral-Large-2411	Q6_K	Fits	15GB	4.0 tok/s
gpt-oss-120b	Q6_K	Fits	22GB	73.4 tok/s
Llama-4-Scout-17B-16E	Q8_0	Tight	1GB	17.0 tok/s
Qwen3-Coder-Next	Q8_0	Fits	34GB	96.3 tok/s
Llama-3.3-70B	Q8_0	Fits	42GB	5.4 tok/s
Qwen3.5-35B-A3B	BF16	Fits	49GB	51.2 tok/s
Qwen3-32B	BF16	Fits	53GB	6.2 tok/s
Gemma-4-31B	BF16	Fits	56GB	6.5 tok/s
Qwen3-30B-A3B	BF16	Fits	57GB	46.5 tok/s
Gemma-3-27B	BF16	Fits	63GB	7.4 tok/s
Qwen3.6-27B	BF16	Fits	64GB	7.4 tok/s
Gemma-4-26B-A4B	BF16	Fits	68GB	40.4 tok/s
Devstral-Small-2507	BF16	Fits	69GB	8.3 tok/s
gpt-oss-20b	BF16	Fits	76GB	42.6 tok/s
Phi-4	BF16	Fits	89GB	14.3 tok/s
Gemma-4-12B	BF16	Fits	94GB	16.7 tok/s
Qwen3-VL-8B-Instruct	BF16	Fits	102GB	24.9 tok/s
Gemma-3n-E4B	BF16	Fits	105GB	49.9 tok/s
Qwen3-4B	BF16	Fits	110GB	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.