Can the Tesla P100 run Qwen3 14B?
Yes. Qwen3 14B needs about 11 GB and the Tesla P100 has 12 GB of VRAM. Expect about 43 tok/s, faster than you can read.
ollama run qwen3:14bFirst time? Install Ollama, then paste that into a terminal.
Qwen3 14B needsAbout 11 GB
Tesla P100 has12 or 16 GB VRAM
Bandwidth732 GB/s
Estimated speed~43 tok/s
By memory size
Each Tesla P100 version
- 12 GBRuns great ~43 tok/s
- 16 GBRuns great ~43 tok/s
Want it faster?
Speed comes from memory bandwidth: the card reads all 9.3 GB of active weights for every token. On the Tesla P100, gpt-oss 20B runs at about 130 tok/s if you can trade some quality for speed. Cards that run Qwen3 14B 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