OpenAI

Can the Arc Pro B60 run gpt-oss 20B?

Published Oct 27, 2026 Updated Oct 27, 2026

We earn from qualifying purchases via affiliate links. Disclosure.

Verdict

Yes. gpt-oss 20B is a 14 GB download (MXFP4 (as shipped)). The Arc Pro B60 gives the GPU 24 GB, leaving about 10 GB for context and runtime (our arithmetic).

Prices: Newegg checked Oct 27, 2026, about 12:35 PM CT; Minisforum checked Oct 27, 2026, 12:40 PM CT. New condition only.

Does it fit?

gpt-oss 20B memory	14 GB at MXFP4 (as shipped) (Ollama: gpt-oss tags)
Arc Pro B60 GPU memory	24 GB of VRAM (product listing).
Left over	About 10 GB (our arithmetic)
Verdict	Fits 4 GB or more to spare (our estimate bands)

Recommended quantization and context

Use the MXFP4 (as shipped) build that Ollama's tag downloads; the memory figure above is for that build. The model supports up to 128K of context, but longer context uses more memory. Ollama starts at a 4096-token context by default (Ollama FAQ).

With about 10 GB spare you have room to raise the context. Raise it in steps and re-check with ollama ps.

Run it

ollama run gpt-oss:20b

Then check it's on the GPU:

ollama ps

The PROCESSOR column should read 100% GPU. Driver setup for Intel cards on Windows, Linux and macOS, plus common fixes, is in the install and run section.

Leaderboard: #269 on LMArena Text (score 1317 ± 6), checked Oct 27, 2026, 2:16 PM CT. Speed isn't listed here because we have no sourced number for this combination.

Where to buy the Arc Pro B60

ASRock Intel Arc Pro B60 Creator 24GB

Price shown at Amazon

Sold at Amazon.

Check price at Amazon

FAQ

Can the Arc Pro B60 run gpt-oss 20B?

Yes: gpt-oss 20B needs 14 GB (MXFP4 (as shipped), Ollama library) and the Arc Pro B60 gives the GPU 24 GB, leaving about 10 GB. That leaves room to raise the context above the 4096-token default. The fit bands are our estimate.

How much VRAM does gpt-oss 20B need?

14 GB for the MXFP4 (as shipped) build in the Ollama library, plus roughly 1–4 GB for context and runtime (our estimate). See the 16 GB page for other models that fit.

What command runs gpt-oss 20B?

ollama run gpt-oss:20b. Then run "ollama ps" and check the PROCESSOR column reads 100% GPU.

How fast is gpt-oss 20B on the Arc Pro B60?

We don't list a speed because we have no sourced measurement for this pairing. Speed depends on memory bandwidth, quantization and context length.

Keep reading

Sources

Each source was opened on Oct 27, 2026.