Mac Studio, M5 Ultra, 96GB

1TB of storage, 1.2TB/s of memory bandwidth, and 88GB of unified memory left for a model once macOS has taken its share. It holds 19 of the 30 models we track.

Offers

checked 50 minutes ago

Applelist pricecheapest todayin stockchecked 50 minutes ago$5,499
Best Buyin stockchecked 46 days ago$5,499
The largest M5 Ultra Best Buy carries. B&H's Payboo card covers the sales tax, which is worth more on a Mac this expensive than any price difference on this page. Adorama's own card does not: it gives 5% back and excludes tax.

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

Timing

Buy now. $5,499 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-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-2411Q4_K_M
Fits10GB headroomest. 10.5 tok/s
gpt-oss-120bQ5_K_M
Tight4GB headroomest. 166 tok/s
Llama-4-Scout-17B-16EQ5_K_M
Fits8GB headroomest. 49.8 tok/s
Qwen3-Coder-NextQ8_0
Tight2GB headroomest. 188 tok/s
Llama-3.3-70BQ8_0
Fits10GB headroomest. 10.5 tok/s
Qwen3.5-35B-A3BBF16
Fits17GB headroomest. 100 tok/s
Qwen3-32BBF16
Fits21GB headroomest. 12.2 tok/s
Gemma-4-31BBF16
Fits24GB headroomest. 12.7 tok/s
Qwen3-30B-A3BBF16
Fits25GB headroomest. 90.9 tok/s
Gemma-3-27BBF16
Fits31GB headroomest. 14.4 tok/s
Qwen3.6-27BBF16
Fits33GB headroomest. 14.4 tok/s
Gemma-4-26B-A4BBF16
Fits36GB headroomest. 78.9 tok/s
Devstral-Small-2507BF16
Fits38GB headroomest. 16.3 tok/s
gpt-oss-20bBF16
Fits45GB headroomest. 83.3 tok/s
Phi-4BF16
Fits57GB headroomest. 27.9 tok/s
Gemma-4-12BBF16
Fits63GB headroomest. 32.6 tok/s
Qwen3-VL-8B-InstructBF16
Fits70GB headroomest. 48.8 tok/s
Gemma-3n-E4BBF16
Fits73GB headroomest. 97.5 tok/s
Qwen3-4BBF16
Fits78GB 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	—	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	Q4_K_M	Fits	10GB	10.5 tok/s
gpt-oss-120b	Q5_K_M	Tight	4GB	166 tok/s
Llama-4-Scout-17B-16E	Q5_K_M	Fits	8GB	49.8 tok/s
Qwen3-Coder-Next	Q8_0	Tight	2GB	188 tok/s
Llama-3.3-70B	Q8_0	Fits	10GB	10.5 tok/s
Qwen3.5-35B-A3B	BF16	Fits	17GB	100 tok/s
Qwen3-32B	BF16	Fits	21GB	12.2 tok/s
Gemma-4-31B	BF16	Fits	24GB	12.7 tok/s
Qwen3-30B-A3B	BF16	Fits	25GB	90.9 tok/s
Gemma-3-27B	BF16	Fits	31GB	14.4 tok/s
Qwen3.6-27B	BF16	Fits	33GB	14.4 tok/s
Gemma-4-26B-A4B	BF16	Fits	36GB	78.9 tok/s
Devstral-Small-2507	BF16	Fits	38GB	16.3 tok/s
gpt-oss-20b	BF16	Fits	45GB	83.3 tok/s
Phi-4	BF16	Fits	57GB	27.9 tok/s
Gemma-4-12B	BF16	Fits	63GB	32.6 tok/s
Qwen3-VL-8B-Instruct	BF16	Fits	70GB	48.8 tok/s
Gemma-3n-E4B	BF16	Fits	73GB	97.5 tok/s
Qwen3-4B	BF16	Fits	78GB	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.