Skip to main content

Can the RTX PRO 6000 Blackwell 96GB Run gpt-oss-20b?

Runs

Yes. gpt-oss-20b at MXFP4 is a 12.1 GB download (Hugging Face file listing for ggml-org/gpt-oss-20b-GGUF), and the RTX PRO 6000 Blackwell 96GB has 96 GB of VRAM, leaving about 83.9 GB for the KV cache and runtime. No published speed measurement for this pair passes SpecPicks' sanity checks yet, so no tokens-per-second figure is quoted.

Model file12.1 GBMXFP4
VRAM96 GBRTX PRO 6000 Blackwell 96GB
Headroom83.9 GBafter weights
Median speed0 cited runs
Bandwidth ceiling~862 tok/s1792 GB/s ÷ 2.1 GB

Buy the RTX PRO 6000 Blackwell 96GB

No new listing for this card is tracked on Amazon today; it mostly trades used.

Published runs for gpt-oss-20b on the RTX PRO 6000 Blackwell 96GB

No published run for this pair has passed the checks yet.

More about this pair

How much VRAM does gpt-oss-20b need?

The MXFP4 file is 12.1 GB. Add roughly 1.5 GB for the runtime and an ~8K-token context, so about 13.6 GB of VRAM holds it comfortably. Longer contexts grow the KV cache and need more.

What is the fastest gpt-oss-20b can generate on the RTX PRO 6000 Blackwell 96GB?

gpt-oss-20b is a mixture-of-experts model that reads about 2.1 GB of active weights per token. At the RTX PRO 6000 Blackwell 96GB's 1792 GB/s of memory bandwidth, that sets a ceiling near 862 tokens per second. Real runs land below it.

Check another pair

See the full matrix → · All RTX PRO 6000 Blackwell 96GB benchmarks →

gpt-oss-20b on other GPUs

Other models on the RTX PRO 6000 Blackwell 96GB

How the checks work

The fit is the MXFP4 file size against the card's VRAM, with 1.5 GB kept for the runtime and an ~8K context. A published run counts only if the pair fits, the run is Q4-class, its source does not call it an estimate, it is under the bandwidth ceiling above, and it is not one figure pasted across many cards. The whole matrix is downloadable as a CSV under CC BY 4.0.

As an Amazon Associate, SpecPicks earns from qualifying purchases.

This page is editorial synthesis based on publicly available information. No independent first-party benchmarking is reported.