text model · gpt-oss · Windows
Can I run gpt-oss 20B on Nvidia GeForce RTX 3060 (12GB)?
No. gpt-oss 20B needs ~13.2 GB even at Q4_K_M, but Nvidia GeForce RTX 3060 (12GB) only has ~11 GB usable.
Needs ~13.2 GB even at Q4_K_M, but only ~11 GB is usable.
- Q4_K_M needed
- ~13.2 GB
- Usable on device
- ~11 GB
- Device memory
- 12 GB
- Parameters
- 21B (MoE, 3.6B active)
- Q4_K_M size
- 11.28 GB
- Context
- 128k
- Ollama tag
- gpt-oss:20b
- Memory
- 12 GB vram
- Usable for weights
- ~11 GB
- Best runtime
- Ollama (CUDA) / llama.cpp CUDA
What you can run instead
Run gpt-oss 20B on other hardware
FAQ
Can Nvidia GeForce RTX 3060 (12GB) run gpt-oss 20B?
No. gpt-oss 20B needs ~13.2 GB even at Q4_K_M, but Nvidia GeForce RTX 3060 (12GB) only has ~11 GB usable.
How much memory does gpt-oss 20B need?
Nvidia GeForce RTX 3060 (12GB) does not have enough memory. At Q4_K_M the weights are ~11.28 GB; with KV cache and runtime overhead, budget ~13.2 GB at a 4k context. It is a Mixture-of-Experts model (21B total / 3.6B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run gpt-oss 20B on Windows?
LM Studio for a simple setup; Ollama (CUDA) for the most speed. AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
Sources
Memory figures are estimates. See methodology.