Can the H100 run Qwen3 235B-A22B?
No. Qwen3 235B-A22B needs about 144 GB and the H100 has at most 80 GB of VRAM. Ollama can still start it by putting part of the model in system RAM, but it runs several times slower. The most capable model it runs well is gpt-oss 120B, at about 400 tok/s.
Qwen3 235B-A22B needsAbout 144 GB
H100 has80 GB VRAM
Bandwidth3350 GB/s
Estimated speedDoesn't fit
What runs Qwen3 235B-A22B
These cards have the memory for it, nearest to the H100 first. The cheapest build on our list that runs it well is the Dell DSS 8440 + 10× Tesla P100, from $5,100 used, at about 19 tok/s.
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