Leaderboard/gpt-oss-20b/RTX 5090 (32GB)/r_b9ul-vxh9sc

gpt-oss-20b on RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB

Name: gpt-oss-20b on RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB
Creator: llm-speed
License: https://creativecommons.org/licenses/by/4.0/
Keywords: LLM benchmark, tokens per second, gpt-oss-20b, RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB, llama.cpp

RTX 5090 (32GB) + AMD Ryzen 7 9850X3D 8-Core Processor (8c) + 30GB

suite suite-v1

cli 0.0.3

signed0tv44ISLy1…

Embed badgesubmitted Jul 01, 2026

https://llm-speed.com/r/r_b9ul-vxh9sc

Workload results

Workload	Backend	Model	decode tok/s	prefill tok/s	TTFT	p50	p95
chat-short	llama.cpp	gpt-oss-20b	318.4tok/s	—	173ms	3.1ms	3.2ms
chat-long	llama.cpp	gpt-oss-20b	301.6tok/s	—	239ms	3.3ms	3.4ms
concurrent-decode	llama.cpp	gpt-oss-20b	302.8tok/s	—	—	3.2ms	3.3ms
agent-trace	llama.cpp	gpt-oss-20b	304.5tok/s	26,907.5tok/s	77.7ms	3.3ms	3.4ms

Reproduce on your machine

Same workload, same model, signed at your rig. The exact command that produced this run:

$ pipx install llm-speed && llm-speed bench --model gpt-oss-20b --workload 'chat-short'

Runs in about a minute. Your number lands on the leaderboard signed and linkable. How it's measured.

Embed this run

Drop the badge into a README, blog post, or signature. Each render is a backlink to the signed result.

[![llm-speed: 318 tok/s on RTX 5090 (32GB) (gpt-oss-20b)](https://llm-speed.com/badge/r_b9ul-vxh9sc.svg)](https://llm-speed.com/r/r_b9ul-vxh9sc)

Related benchmarks

More gpt-oss-20b benchmarks — every backend and rig that has run this model.
More RTX 5090 (32GB) LLM benchmarks — every model measured on this hardware.

Provenance

Run ID: r_b9ul-vxh9sc
Fingerprint hash: 013ca61a09d17996
Public key: 0tv44ISLy10gz6Oc6FJig3eWJVLwso9oKemSM4nicKM=
Received: 2026-07-01 08:53:25