Quantized version of ArliAI/gpt-oss-120b-Derestricted
Same MXFP4 format as the original GPT-OSS-120b
For a pro 6000 on vllm v0.12:
vllm serve justinjja/gpt-oss-120b-Derestricted-MXFP4 --tool-call-parser openai --reasoning-parser openai_gptoss --enable-auto-tool-choice
- Downloads last month
- 201
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support