Can the RTX 2060 run gpt-oss 20B?
No. gpt-oss 20B needs about 16 GB and the RTX 2060 has at most 12 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 Gemma 3 12B, at about 23 tok/s.
gpt-oss 20B needsAbout 16 GB
RTX 2060 has6 or 12 GB VRAM
Bandwidth336 GB/s
Estimated speedDoesn't fit
By memory size
Each RTX 2060 version
- 6 GBToo big
- 12 GBToo big
What runs gpt-oss 20B
These cards have the memory for it, nearest to the RTX 2060 first. The cheapest build on our list that runs it well is the Used workstation + 2× Tesla P100, from $750 used, at about 130 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