self-hosted/ai
§01·compatibility · /check

gpt-oss 20B on RTX 5090

Yes — gpt-oss 20B runs on the RTX 5090 (32 GB). Fastest community-measured result: 9443.8 prefill tokens/s.

✓ runsllmactive50 series32GB VRAM
model
name
gpt-oss 20B
slug
gpt-oss-20b
vertical
llm
status
active
repo
huggingface.co ↗
open detail ↗
gpu
name
RTX 5090
slug
rtx-5090
vram
32 GB
series
50
open detail ↗
§02·benchmarks
TaskQuantSpeedVRAMWorksConfidenceSourceVerified
llmQ4_K9443.8prefill tokens/s✓hardware-corner.net· web2026-05-15
llmQ4_K298.2tokens/s✓hardware-corner.net· web2026-05-15
llmQ4_K_XL249.19tokens/s✓hardware-corner.net· web2026-05-15
§03·common questions
Can you run gpt-oss 20B on RTX 5090?

Yes — gpt-oss 20B runs on the RTX 5090 (32 GB). Fastest community-measured result: 9443.8 prefill tokens/s.

Which quantizations have been tested for gpt-oss 20B on RTX 5090?

Q4_K, Q4_K_XL — measured in community benchmarks.

How fast is gpt-oss 20B on RTX 5090?

Up to 9443.8 prefill tokens/s (llm), the fastest community-measured result.

Are there step-by-step instructions for gpt-oss 20B on RTX 5090?

Yes — a step-by-step recipe documents gpt-oss 20B on the RTX 5090; see the recipes listed below.

§04·related recipes