Mac Studio, M5 Ultra, 256GB

1TB of storage, 1.2TB/s of memory bandwidth, and 248GB of unified memory left for a model once macOS has taken its share. It holds 9 of the 11 models we track.

Offers

checked 10 hours ago

Applelist pricecheapest todayin stockchecked 10 hours ago$9,499
B&H Photonot availablechecked 10 hours ago$9,499
Preorder, no ship date shown. B&H advertises a store-card promotion that covers the sales tax — on a Mac at this price that is worth about $800, far more than any price difference here.
Adoramanot availablechecked 10 hours ago$9,499
Special order, ships about 7 Oct.

Every one of the 2 reseller listings we found is $9,499. No reseller undercuts Apple on this Config, so Apple direct is the price to beat.

Timing

Collecting price history — 2 of 90 days. No timing verdict yet.

Models it runs — 8K context

Llama-4-Behemoth—
Won't fit— headroom
DeepSeek-V3—
Won't fit— headroom
Llama-4-Maverick-17B-128EQ4_K_M
Tight4GB headroomest. 58.5 tok/s
Qwen3-235B-A22BQ6_K
Fits53GB headroomest. 33.3 tok/s
Mistral-Large-2411Q8_0
Fits113GB headroomest. 6.0 tok/s
gpt-oss-120bBF16
Tight12GB headroomest. 58.8 tok/s
Llama-4-Scout-17B-16EBF16
Fits27GB headroomest. 17.6 tok/s
Llama-3.3-70BBF16
Fits104GB headroomest. 5.6 tok/s
Qwen3-32BBF16
Fits181GB headroomest. 12.2 tok/s
Gemma-3-27BBF16
Fits191GB headroomest. 14.4 tok/s
gpt-oss-20bBF16
Fits204GB headroomest. 83.3 tok/s

Model	Best quant	Fit	Headroom	Est. speed
Llama-4-Behemoth	—	Won't fit	—	—
DeepSeek-V3	—	Won't fit	—	—
Llama-4-Maverick-17B-128E	Q4_K_M	Tight	4GB	58.5 tok/s
Qwen3-235B-A22B	Q6_K	Fits	53GB	33.3 tok/s
Mistral-Large-2411	Q8_0	Fits	113GB	6.0 tok/s
gpt-oss-120b	BF16	Tight	12GB	58.8 tok/s
Llama-4-Scout-17B-16E	BF16	Fits	27GB	17.6 tok/s
Llama-3.3-70B	BF16	Fits	104GB	5.6 tok/s
Qwen3-32B	BF16	Fits	181GB	12.2 tok/s
Gemma-3-27B	BF16	Fits	191GB	14.4 tok/s
gpt-oss-20b	BF16	Fits	204GB	83.3 tok/s

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