text model · gpt-oss · Windows
Can I run gpt-oss 20B on Nvidia GeForce RTX 4090 (24GB)?
Yes. gpt-oss 20B runs on Nvidia GeForce RTX 4090 (24GB) at Q4_K_M (~13.2 GB of ~23 GB usable).
Runs at Q4_K_M using ~13.2 GB of ~23 GB usable.
- Q4_K_M needed
- ~13.2 GB
- Usable on device
- ~23 GB
- Device memory
- 24 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run gpt-oss:20b llama-cli -hf ggml-org/gpt-oss-20b-GGUF:Q4_K_M lms get ggml-org/gpt-oss-20b-GGUF AMD GPUs run via Vulkan/ROCm at roughly half CUDA throughput. NVIDIA is the smooth path on Windows.
- Parameters
- 21B (MoE, 3.6B active)
- Q4_K_M size
- 11.28 GB
- Context
- 128k
- Ollama tag
- gpt-oss:20b
- Memory
- 24 GB vram
- Usable for weights
- ~23 GB
- Best runtime
- vLLM (Linux) / Ollama (CUDA)
You could also run
Run gpt-oss 20B on other hardware
FAQ
Can Nvidia GeForce RTX 4090 (24GB) run gpt-oss 20B?
Yes. gpt-oss 20B runs on Nvidia GeForce RTX 4090 (24GB) at Q4_K_M (~13.2 GB of ~23 GB usable).
How much memory does gpt-oss 20B need?
Nvidia GeForce RTX 4090 (24GB) has room to spare. 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.