what/llm/can/i/run
gpus/apple/m4-max-96gb

M4 Max 96GB

Released 2024-10-30 · Street $4,299
vram
96 GB
unified mem
bandwidth
546
GB/s
models fit
18
top · FP16
power
78 W
low

Spec sheet · top pick

Hardware spec
M4 Max 96GB
Apple · Apple Silicon · M4
vram
96 GB unified
bandwidth
546 GB/s
tdp
78 W
released
2024-10-30
msrp
$4,299
street
~$4,299
★ Sweet spot for this card
gemma 3 27b
FP16 · GGUF · 57.2 GB
bench50.6 · conf A
vram57.2 / 96 GB
speed10 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 GB1050.6Great
02Gemma 2 27BFP1657.2 GB1046.2Great
03Qwen2.5 Coder 32BFP1667.7 GB848.8Great
04Gemma 2 9BFP1619.4 GB2835.0Great
05Gemma 3 12BFP1625.7 GB2131.3Great
06deepseek r1 distill llama 70bQ8_074 GB751.7Great
07Qwen3 32BFP1667.7 GB840.0Great
08deepseek r1 distill qwen 32bFP1667.7 GB833.3Great
09Gemma 3 4BFP168.9 GB6115.1Great
10Mixtral 8x7B v0.1Q8_049.5 GB1113.3Great
Showing 10 of 18 models that fit · see full ranked list →

Upgrade options

★ Best value
+H200 SXM5
141 GB · ~$45,000 · +$40,701 over M4 Max 96GB
Unlocks +1 models not in current rank
See H200 SXM5
Bigger tier
+M1 Ultra 128GB
128 GB · ~$4,000 · +$-299 over M4 Max 96GB
Unlocks +1 models not in current rank
See M1 Ultra 128GB
Premium tier
+M2 Ultra 128GB
128 GB · ~$5,200 · +$901 over M4 Max 96GB
Unlocks +1 models not in current rank
See M2 Ultra 128GB

Also compare

H100 PCIe
80 GB · NVIDIA · 551% more
H100 SXM5
80 GB · NVIDIA · 830% more
A100 80GB
80 GB · NVIDIA · 156% more
M2 Max 96GB
96 GB · Apple unified · 19% cheaper
Not running a M4 Max 96GB?
Tell us what you actually have — we'll re-rank everything for your machine.
Change my machine