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

gpt-oss 20B on RTX 5070 Ti

Yes — gpt-oss 20B runs on the RTX 5070 Ti (16 GB). Fastest community-measured result: 6178.3 prefill tokens/s, with 16 GB peak VRAM.

runsllmactive50 series16GB VRAM
model
name
gpt-oss 20B
slug
gpt-oss-20b
vertical
llm
status
active
open detail ↗
gpu
name
RTX 5070 Ti
slug
rtx-5070-ti
vram
16 GB
series
50
open detail ↗
§02·benchmarks
TaskQuantSpeedVRAMWorksConfidenceSourceVerified
llmMXFP46178.3prefill tokens/s16GBhardware-corner.net· web2026-05-15
llmMXFP4156tokens/s16GBhardware-corner.net· web2026-05-15
§03·common questions
Can you run gpt-oss 20B on RTX 5070 Ti?

Yes — gpt-oss 20B runs on the RTX 5070 Ti (16 GB). Fastest community-measured result: 6178.3 prefill tokens/s, with 16 GB peak VRAM.

How much VRAM does gpt-oss 20B need on RTX 5070 Ti?

Measured peak VRAM is 16 GB.

Which quantizations have been tested for gpt-oss 20B on RTX 5070 Ti?

MXFP4 — measured in community benchmarks.

How fast is gpt-oss 20B on RTX 5070 Ti?

Up to 6178.3 prefill tokens/s (llm), the fastest community-measured result.

Are there step-by-step instructions for gpt-oss 20B on RTX 5070 Ti?

Yes — a step-by-step recipe documents gpt-oss 20B on the RTX 5070 Ti; see the recipes listed below.

§04·related recipes