🧩 Model Card: gpt-oss-20b

▶️ Run with FastFlowLM in PowerShell:

flm run gpt-oss:20b

Default reasoning effort for both CLI and Server Modes is Medium

Set reasoning effort (CLI):

# CLI
flm run gpt-oss:20b
/set r-eff high

📝 NOTE

  • Memory Requirements
    ⚠️ Note: Running gpt-oss:20b may need a system with > 32 GB RAM. The model itself uses ~15.1 GB of memory in FLM, and there is an internal cap (~15.6 GB) on NPU memory allocation enforced by AMD/Microsoft, which makes only about half of the total system RAM available to the NPU. On 32 GB machines, it sometimes works and sometimes does not, so we recommend more RAM for a smooth experience.

🧩 Model Card: gpt-oss-safeguard-20b

▶️ Run with FastFlowLM in PowerShell:

flm run gpt-oss-safeguard:20b

Default reasoning effort for both CLI and Server Modes is Medium

Set reasoning effort (CLI):

# CLI
flm run gpt-oss:20b
/set r-eff high

📝 NOTE

  • Memory Requirements
    ⚠️ Note: Running gpt-oss-safeguard:20b may need a system with > 32 GB RAM. The model itself uses ~15.1 GB of memory in FLM, and there is an internal cap (~15.6 GB) on NPU memory allocation enforced by AMD/Microsoft, which makes only about half of the total system RAM available to the NPU. On 32 GB machines, it sometimes works and sometimes does not, so we recommend more RAM for a smooth experience.