Can the Tesla V100 run Llama 3.3 70B?
No. Llama 3.3 70B needs about 45 GB and the Tesla V100 has at most 32 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 Qwen3 32B, at about 25 tok/s.
Llama 3.3 70B needsAbout 45 GB
Tesla V100 has16 or 32 GB VRAM
Bandwidth900 GB/s
Estimated speedDoesn't fit
By memory size
Each Tesla V100 version
- 16 GBToo big
- 32 GBToo big
What runs Llama 3.3 70B
These cards have the memory for it, nearest to the Tesla V100 first. The cheapest build on our list that runs it well is the Workstation + 2× RTX 3090, from $3,500 used, at about 12 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