LocalClaw/LLM/GPT-OSS (120B)
Open-weight local LLM

GPT-OSS (120B)

Catalogue summary: 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.

Repository editorial metadata; verify comparative claims in the linked upstream material.

96 GB catalogue minimum96 GB RAMMXFP4Coding assistant
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
117B (5.1B active)
Minimum RAM
96 GB
Model size
63 GB
Quantization
MXFP4

Can GPT-OSS (120B) run locally?

GPT-OSS (120B) has a catalogue minimum of 96 GB RAM with MXFP4. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use gpt-oss-120b as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): ggml-org/gpt-oss-120b-GGUFUpstream releasePaper or model cardLicence text
chatcodereasoningbeastgeneral

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.

Catalogue record

  • Family: gpt-oss
  • Parameters: 117B (5.1B active)
  • Recommended quantization: MXFP4
  • Catalogue minimum RAM: 96 GB
  • Catalogue model size: 63 GB
  • Tags: chat, code, reasoning, beast, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • code
  • reasoning
  • beast
  • general

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
2
quality
10
coding
10
reasoning
10

Technical notes

Developer
OpenAI
License
Apache 2.0
Context window
131,072 tokens
Architecture
Sparse MoE Transformer with 117B total parameters, 5.1B active parameters, 128 experts and 128K context

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.

Large unified memoryMac Studio M4 Max 128GB128GB AI PC classNVIDIA GB10 / DGX SparkHigh-memory picks128GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

GPT-OSS (20B) 20BHy3 295B (21B active)K2-Horizon-MoVA-36B-A4B 36B (4B active, MoE)Laguna S 2.1 118B (8B active, MoE)Command A (111B) 111BGLM 4.5 Air (MoE) 106B (12B active, MoE)Mistral Small 4 (119B-A6.5B) 119B (6.5B active, MoE)WizardLM 2 (8x22B) 8x22B (141B total)

Where to go next