Can the H200 run Llama 3.3 70B?
Yes. Llama 3.3 70B needs about 45 GB and the H200 has 141 GB of VRAM. Expect about 61 tok/s, faster than you can read.
ollama run llama3.3:70bFirst time? Install Ollama, then paste that into a terminal.
Llama 3.3 70B needsAbout 45 GB
H200 has141 GB VRAM
Bandwidth4800 GB/s
Estimated speed~61 tok/s
Want it faster?
Speed comes from memory bandwidth: the card reads all 43 GB of active weights for every token. On the H200, gpt-oss 120B runs at about 580 tok/s if you can trade some quality for speed. Cards that run Llama 3.3 70B faster:
No single card or Mac we track does. It needs a multi-GPU rig; see the builds.
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