CanItRun Logocanitrun.

GPT-OSS 20B

GPT-OSS 20B needs roughly 12.2GB VRAM at Q4_K_M quantization (47.5GB at FP16). 61 GPUs we track can run it fully in VRAM at 8k context.

OpenAI21B params4B active (MoE)128k contextApache 2.0Commercial use ok

VRAM at each quantization

Assumes 8k context. KV cache grows linearly with context length.

QuantWeightsKV cacheTotal
FP1642.0 GB0.40 GB47.5 GB
Q821.0 GB0.40 GB24.0 GB
Q6_K15.8 GB0.40 GB18.1 GB
Q5_K_M13.1 GB0.40 GB15.2 GB
Q4_K_M10.5 GB0.40 GB12.2 GB
Q3_K_M8.4 GB0.40 GB9.9 GB
Q2_K6.3 GB0.40 GB7.5 GB

Benchmarks

GPQA
71.5

GPUs that run GPT-OSS 20B natively (61)

Plus 1 GPUs that run it with CPU offload (slower)

Notes

Smaller sibling of GPT-OSS 120B. Matches o3-mini on key benchmarks; runs on 16 GB of VRAM.

Hugging Face ↗Released 2025-08-05