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 25 of the 30 models we track.

Offers

checked 1 hour ago

Adoramanot availablechecked 46 days ago$9,499
Special order, ships about 7 Oct.
Applelist pricecheapest todayin stockchecked 1 hour ago$9,499
B&H Photonot availablechecked 46 days ago$9,499
Preorder, no ship date shown. B&H's Payboo card covers the sales tax — on a Mac at this price that is worth about $800, far more than any price difference here.

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

Buy now. $9,499 is the lowest price in 47 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-InstructQ3_K_M
Tight10GB headroomest. 35.1 tok/s
Llama-4-Maverick-17B-128EQ4_K_M
Tight4GB headroomest. 58.5 tok/s
GLM-4.6Q4_K_M
Fits28GB headroomest. 31.1 tok/s
DeepSeek-V4-FlashQ6_K
Tight14GB headroomest. 56.3 tok/s
Qwen3-235B-A22BQ6_K
Fits53GB headroomest. 33.3 tok/s
MiniMax-M2Q8_0
Tight1GB headroomest. 56.5 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
Qwen3-Coder-NextBF16
Fits87GB headroomest. 100 tok/s
Llama-3.3-70BBF16
Fits104GB headroomest. 5.6 tok/s
Qwen3.5-35B-A3BBF16
Fits177GB headroomest. 100 tok/s
Qwen3-32BBF16
Fits181GB headroomest. 12.2 tok/s
Gemma-4-31BBF16
Fits184GB headroomest. 12.7 tok/s
Qwen3-30B-A3BBF16
Fits185GB headroomest. 90.9 tok/s
Gemma-3-27BBF16
Fits191GB headroomest. 14.4 tok/s
Qwen3.6-27BBF16
Fits192GB headroomest. 14.4 tok/s
Gemma-4-26B-A4BBF16
Fits196GB headroomest. 78.9 tok/s
Devstral-Small-2507BF16
Fits197GB headroomest. 16.3 tok/s
gpt-oss-20bBF16
Fits204GB headroomest. 83.3 tok/s
Phi-4BF16
Fits217GB headroomest. 27.9 tok/s
Gemma-4-12BBF16
Fits222GB headroomest. 32.6 tok/s
Qwen3-VL-8B-InstructBF16
Fits230GB headroomest. 48.8 tok/s
Gemma-3n-E4BBF16
Fits233GB headroomest. 97.5 tok/s
Qwen3-4BBF16
Fits238GB headroomest. 97.5 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	Q3_K_M	Tight	10GB	35.1 tok/s
Llama-4-Maverick-17B-128E	Q4_K_M	Tight	4GB	58.5 tok/s
GLM-4.6	Q4_K_M	Fits	28GB	31.1 tok/s
DeepSeek-V4-Flash	Q6_K	Tight	14GB	56.3 tok/s
Qwen3-235B-A22B	Q6_K	Fits	53GB	33.3 tok/s
MiniMax-M2	Q8_0	Tight	1GB	56.5 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
Qwen3-Coder-Next	BF16	Fits	87GB	100 tok/s
Llama-3.3-70B	BF16	Fits	104GB	5.6 tok/s
Qwen3.5-35B-A3B	BF16	Fits	177GB	100 tok/s
Qwen3-32B	BF16	Fits	181GB	12.2 tok/s
Gemma-4-31B	BF16	Fits	184GB	12.7 tok/s
Qwen3-30B-A3B	BF16	Fits	185GB	90.9 tok/s
Gemma-3-27B	BF16	Fits	191GB	14.4 tok/s
Qwen3.6-27B	BF16	Fits	192GB	14.4 tok/s
Gemma-4-26B-A4B	BF16	Fits	196GB	78.9 tok/s
Devstral-Small-2507	BF16	Fits	197GB	16.3 tok/s
gpt-oss-20b	BF16	Fits	204GB	83.3 tok/s
Phi-4	BF16	Fits	217GB	27.9 tok/s
Gemma-4-12B	BF16	Fits	222GB	32.6 tok/s
Qwen3-VL-8B-Instruct	BF16	Fits	230GB	48.8 tok/s
Gemma-3n-E4B	BF16	Fits	233GB	97.5 tok/s
Qwen3-4B	BF16	Fits	238GB	97.5 tok/s

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