Can the L40S run gpt-oss 120B?
No. gpt-oss 120B needs about 67 GB and the L40S has at most 48 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 24 tok/s.
gpt-oss 120B needsAbout 67 GB
L40S has48 GB VRAM
Bandwidth864 GB/s
Estimated speedDoesn't fit
What runs gpt-oss 120B
These cards have the memory for it, nearest to the L40S first. The cheapest build on our list that runs it well is the Ryzen AI Max+ 395 mini PC, 128 GB, from $3,400 used, at about 31 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