L
localai.computer
ModelsGPUsSystemsAI SetupsBuildsOpenClawMethodology

Resources

  • Methodology
  • Submit Benchmark
  • About

Browse

  • AI Models
  • GPUs
  • PC Builds

Guides

  • OpenClaw Guide
  • How-To Guides

Legal

  • Privacy
  • Terms
  • Contact

© 2025 localai.computer. Hardware recommendations for running AI models locally.

ℹ️We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

Can RX 9070 XT run openai/gpt-oss-20b?

Runs Q416GB VRAM availableRequires 10GB+

RX 9070 XT meets the minimum VRAM requirement for Q4 inference of openai/gpt-oss-20b. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

What this means for you

RX 9070 XT can run openai/gpt-oss-20b with Q4 quantization. At approximately 55 tokens/second, you can expect Good speed - acceptable for interactive use.

You have 6GB headroom, which is sufficient for system overhead and smooth operation.

Quantization breakdown

QuantizationVRAM neededVRAM availableEstimated speedVerdict
Q410GB16GB55.38 tok/s✅ Fits comfortably
Q820GB16GB39.82 tok/s❌ Not recommended
FP1641GB16GB19.82 tok/s❌ Not recommended

Suitable alternatives

AMD Instinct MI300X
192GB
413.08 tok/s
Price: —
NVIDIA H200 SXM 141GB
141GB
396.99 tok/s
Price: —
NVIDIA H100 SXM5 80GB
80GB
296.02 tok/s
Price: —
AMD Instinct MI300X
192GB
292.98 tok/s
Price: —
AMD Instinct MI250X
128GB
282.04 tok/s
Price: —

More questions

RX 9070 XT specs & pricingFull guide for openai/gpt-oss-20bopenai/gpt-oss-20b speed on RX 9070 XTopenai/gpt-oss-20b Q4 requirements