what/llm/can/i/run
gpus/apple/m3-max-128gb

M3 Max 128GB

Released 2023-10-30 · Street $4,999
vram
128 GB
unified mem
bandwidth
400
GB/s
models fit
19
top · FP16
power
78 W
low

Spec sheet · top pick

Hardware spec
M3 Max 128GB
Apple · Apple Silicon · M3
vram
128 GB unified
bandwidth
400 GB/s
tdp
78 W
released
2023-10-30
msrp
$4,999
street
~$4,999
★ Sweet spot for this card
gemma 3 27b
FP16 · GGUF · 57.2 GB
bench50.6 · conf A
vram57.2 / 128 GB
speed7 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 GB750.6Great
02Qwen2.5 Coder 32BFP1667.7 GB648.8Great
03Gemma 2 9BFP1619.4 GB2135.0Great
04Gemma 2 27BFP1657.2 GB746.2Great
05deepseek r1 distill llama 70bQ8_074 GB551.7Great
06Qwen3 32BFP1667.7 GB640.0Great
07Gemma 3 12BFP1625.7 GB1631.3Great
08deepseek r1 distill qwen 32bFP1667.7 GB633.3Great
09Gemma 3 4BFP168.9 GB4515.1Great
10Mixtral 8x22b v0.1Q6_K111.5 GB420.0Ok
Showing 10 of 19 models that fit · see full ranked list →

Upgrade options

★ Best value
+H200 SXM5
141 GB · ~$45,000 · +$40,001 over M3 Max 128GB
Same model set · higher headroom for context / batch
See H200 SXM5
Bigger tier
+M2 Ultra 192GB
192 GB · ~$6,200 · +$1,201 over M3 Max 128GB
Unlocks +1 models not in current rank
See M2 Ultra 192GB
Premium tier
+M3 Ultra 192GB
192 GB · ~$5,599 · +$600 over M3 Max 128GB
Unlocks +1 models not in current rank
See M3 Ultra 192GB

Also compare

H200 SXM5
141 GB · NVIDIA · 800% more
M1 Ultra 128GB
128 GB · Apple unified · 20% cheaper
M2 Ultra 128GB
128 GB · Apple unified · 4% more
M4 Max 128GB
128 GB · Apple unified · 6% cheaper
Not running a M3 Max 128GB?
Tell us what you actually have — we'll re-rank everything for your machine.
Change my machine