what/llm/can/i/run
gpus/nvidia/a100-80gb

A100 80GB

Released 2020-11-16 · Street $11,000
vram
80 GB
discrete
bandwidth
1,935
GB/s
models fit
18
top · FP16
power
400 W
high

Spec sheet · top pick

Hardware spec
A100 80GB
NVIDIA · Ampere · sm_80
vram
80 GB
bandwidth
1,935 GB/s
tdp
400 W
released
2020-11-16
msrp
$15,000
street
~$11,000
★ Sweet spot for this card
gemma 3 27b
FP16 · GGUF · 57.2 GB
bench50.6 · conf A
vram57.2 / 80 GB
speed34 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 GB3450.6Great
02Qwen2.5 Coder 32BFP1667.7 GB2948.8Great
03Gemma 2 27BFP1657.2 GB3446.2Great
04Qwen3 32BFP1667.7 GB2940.0Great
05deepseek r1 distill llama 70bQ8_074 GB2651.7Ok
06Gemma 2 9BFP1619.4 GB10035.0Great
07Gemma 3 12BFP1625.7 GB7531.3Great
08deepseek r1 distill qwen 32bFP1667.7 GB2933.3Great
09Mixtral 8x22b v0.1Q4_K_M74.5 GB2620.0Ok
10Gemma 3 4BFP168.9 GB21715.1Great
Showing 10 of 18 models that fit · see full ranked list →

Upgrade options

★ Best value
+H200 SXM5
141 GB · ~$45,000 · +$34,000 over A100 80GB
Unlocks +1 models not in current rank
See H200 SXM5
Bigger tier
+M1 Ultra 128GB
128 GB · ~$4,000 · +$-7,000 over A100 80GB
Unlocks +1 models not in current rank
See M1 Ultra 128GB
Premium tier
+M2 Max 96GB
96 GB · ~$3,500 · +$-7,500 over A100 80GB
Same model set · higher headroom for context / batch
See M2 Max 96GB

Also compare

H100 PCIe
80 GB · NVIDIA · 155% more
H100 SXM5
80 GB · NVIDIA · 264% more
M1 Max 64GB
64 GB · Apple unified · 79% cheaper
M1 Ultra 64GB
64 GB · Apple unified · 77% cheaper
Not running a A100 80GB?
Tell us what you actually have — we'll re-rank everything for your machine.
Change my machine