Open-weight local LLM
GPT-OSS (120B)
OpenAI flagship open-weight reasoning model. 128K context, strong tool use and Apache 2.0 licensing, now practical for 96GB+ local workstations via GGUF MXFP4.
Large-memory workstation
96 GB RAM
MXFP4
High-end local reasoning
Parameters
117B (5.1B active)
Minimum RAM
96 GB
Model size
63 GB
Quantization
MXFP4
Can GPT-OSS (120B) run locally?
GPT-OSS (120B) needs a serious workstation with large unified memory or high VRAM.
Search for gpt-oss-120b in LM Studio or another GGUF-compatible runtime.
ggerganov/gpt-oss-120b-GGUFchatcodereasoningbeastgeneral
Install path
01
Check RAM fitMinimum 96 GB RAM. Start with the MXFP4 quant.02
Load the modelSearch gpt-oss-120b in LM Studio.03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.Strengths
- Flagship OpenAI open-weight reasoning model
- Apache 2.0 license
- Near o4-mini-class reasoning target
- 128K context
- Strong coding and tool-use behavior
Limitations
- Needs a 96GB+ workstation or single 80GB GPU class setup
- Large MXFP4 GGUF download
- Slow on CPU-only systems
Best use cases
- High-end local reasoning
- Coding agents
- Tool-use workflows
- Research comparison
- Private workstation inference
Capability profile
Technical notes
This model fits these next steps
Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.