← Everything the H100 runsH100 · Llama 3.3 70B

Can the H100 run Llama 3.3 70B?

Yes. Llama 3.3 70B needs about 45 GB and the H100 has 80 GB of VRAM. Expect about 43 tok/s, faster than you can read.

ollama run llama3.3:70b

First time? Install Ollama, then paste that into a terminal.

Llama 3.3 70B needsAbout 45 GB
H100 has80 GB VRAM
Bandwidth3350 GB/s
Estimated speed~43 tok/s
Want it faster?

Speed comes from memory bandwidth: the card reads all 43 GB of active weights for every token. On the H100, gpt-oss 120B runs at about 400 tok/s if you can trade some quality for speed. Cards that run Llama 3.3 70B faster:

How we estimate

Speed is roughly memory bandwidth divided by the weights read per token, calibrated on our own rack. Sizes are Ollama's default 4-bit downloads plus about 1.2 GB for context. Real results are usually within about a third. Measured it yourself? Send us the number.

Keep going

More about the H100 and Llama 3.3 70B