← CanIRunLocal · All hardware · All models
Yes, with partial offload (slower). gpt-oss 20B (MoE, MXFP4) on RTX 4060 8GB at MXFP4 uses system RAM (15.1 GB needed, 7.5 GB usable), about 13 tok/s (estimate).
Hardware: RTX 4060 8GB · Model: gpt-oss 20B (MoE, MXFP4)
RTX 4060 8GB has 8 GB of VRAM and 272 GB/s of memory bandwidth. The checker holds back 0.5 GB of VRAM for the driver and assumes 16 GB of system RAM, so fast memory usable by Ollama is 7.5 GB. Partial offload may also use 60% of that system RAM. gpt-oss 20B (MoE, MXFP4) (20.9B, 3.6B active, OpenAI) at MXFP4 is a 14 GB download and needs 15.1 GB with headroom for about 8k tokens.
| Best quant | MXFP4 |
|---|---|
| Download size | 14 GB |
| Memory needed | 15.1 GB |
| Usable fast memory | 7.5 GB |
| Fit | partial offload (slower) |
| Estimated speed | ~13 tok/s (estimate) |
| Command | ollama run gpt-oss:20b |
Estimates, not benchmarks. Model sizes are ollama.com download sizes; memory needed adds headroom for ~8k tokens of context; speeds are rough figures from memory bandwidth. Data updated 2026-10-23.
A project by OnDevice Labs · llms.txt