gpt-oss-20b VRAM Requirements
Developed by OpenAI
Find out exactly how much VRAM you need to run gpt-oss-20b locally. Calculate the memory footprint of different GGUF quantization variants (like Q4_K_M or Q8_0), estimate your context length KV cache VRAM footprint, and determine if your hardware supports a full GPU VRAM offload or if you will need to rely on slow partial CPU offloading to avoid a CUDA Out of Memory (OOM) error.
Hardware Configuration
Adjust settings to check compatibility with your system in real time.
Available: 14.50 GB
Available: 29.00 GB
This model's configuration fits fully in your VRAM. You will experience peak speed and performance.
Requires 14.05 GB total memory (weights: 12.82 GB, context overhead: 0.19 GB, activation overhead: 1.04 GB).
gpt-oss-20b Quantization Formats & VRAM Compatibility
Select a format to set it as active and calculate your system fit dynamically.
| Quant | Weights | KV Cache | Overhead | Total VRAM | Status | Links |
|---|---|---|---|---|---|---|
| Base (Unquantized) | 12.82 GB | 0.19 GB | 1.04 GB | 14.05 GB | Fits in VRAM | HF weights |
gpt-oss-20b KV Cache Memory Breakdown
How to Setup and Run gpt-oss-20b Locally
Method A: Ollama (Recommended)
Ollama is the easiest way to run models in the background. First, download it from ollama.com, then execute this terminal command:
ollama run <model-name>Method B: LM Studio (GUI)
If you prefer a full graphical interface with chat UI and local server hosting:
- Download and install LM Studio.
- Search for gpt-oss-20b in the home page search tab.
- Select a quantization level (like Q4_K_M) that fits your VRAM, click download, and load it to chat.
Model Specs
- DeveloperOpenAI
- Parameter Count21B
- Base File Size12.8 GB
- AvailabilityLocal-Only
- Input ModalitiesText
Standard Benchmark Scores
Commercial API Pricing
This model is self-hosted only or official API pricing is not available.
Model Release Alerts
Get notified when new models drop that run on your hardware. Zero spam.