Can the Tesla V100 run Qwen3 30B-A3B?
Yes, with 32 GB or more. Qwen3 30B-A3B needs about 21 GB and the Tesla V100 has 32 GB of VRAM. Expect about 160 tok/s, faster than you can read. The 16 GB version doesn't have room.
ollama run qwen3:30bFirst time? Install Ollama, then paste that into a terminal.
Qwen3 30B-A3B needsAbout 21 GB
Tesla V100 has16 or 32 GB VRAM
Bandwidth900 GB/s
Estimated speed~160 tok/s
By memory size
Each Tesla V100 version
- 16 GBToo big
- 32 GBRuns great ~160 tok/s
Want it faster?
Speed comes from memory bandwidth: the card reads all 2 GB of active weights for every token. Cards that run Qwen3 30B-A3B 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