what/llm/can/i/run
gpus/apple/m2-ultra-128gb

M2 Ultra 128GB

Released 2023-06-13 · Street $5,200
vram
128 GB
unified mem
bandwidth
800
GB/s
models fit
19
top · FP16
power
120 W
low

Spec sheet · top pick

Hardware spec
M2 Ultra 128GB
Apple · Apple Silicon · M2
vram
128 GB unified
bandwidth
800 GB/s
tdp
120 W
released
2023-06-13
msrp
$5,599
street
~$5,200
★ Sweet spot for this card
gemma 3 27b
FP16 · GGUF · 57.2 GB
bench50.6 · conf A
vram57.2 / 128 GB
speed14 tok/s
Best benchmark per GB of VRAM in your tier. FP16wastes <3% quality vs FP16, leaves headroom for 32k context.
Full model inspect →

Top 10 models on this GPU

#modelquantvramtok/sbench ↓fit
01gemma 3 27bFP1657.2 GB1450.6Great
02Qwen2.5 Coder 32BFP1667.7 GB1248.8Great
03Gemma 2 27BFP1657.2 GB1446.2Great
04deepseek r1 distill llama 70bQ8_074 GB1151.7Great
05Qwen3 32BFP1667.7 GB1240.0Great
06Gemma 2 9BFP1619.4 GB4135.0Great
07Gemma 3 12BFP1625.7 GB3131.3Great
08deepseek r1 distill qwen 32bFP1667.7 GB1233.3Great
09Gemma 3 4BFP168.9 GB9015.1Great
10Mixtral 8x22b v0.1Q6_K111.5 GB720.0Ok
Showing 10 of 19 models that fit · see full ranked list →

Upgrade options

★ Best value
+H200 SXM5
141 GB · ~$45,000 · +$39,800 over M2 Ultra 128GB
Same model set · higher headroom for context / batch
See H200 SXM5
Bigger tier
+M2 Ultra 192GB
192 GB · ~$6,200 · +$1,000 over M2 Ultra 128GB
Unlocks +1 models not in current rank
See M2 Ultra 192GB
Premium tier
+M3 Ultra 192GB
192 GB · ~$5,599 · +$399 over M2 Ultra 128GB
Unlocks +1 models not in current rank
See M3 Ultra 192GB

Also compare

H200 SXM5
141 GB · NVIDIA · 765% more
M1 Ultra 128GB
128 GB · Apple unified · 23% cheaper
M3 Max 128GB
128 GB · Apple unified · 4% cheaper
M4 Max 128GB
128 GB · Apple unified · 10% cheaper
Not running a M2 Ultra 128GB?
Tell us what you actually have — we'll re-rank everything for your machine.
Change my machine