OpenAI · 117B (5.1B active) · 専家混合（MoE）
OpenAI's flagship open-weight MoE — 52.6% SWE-bench 看看你的 GPU 或 Mac 跑不跑得動 GPT-OSS 120B——最低 65.4 GB，建議 109 GB。
専家混合（MoE）
| 量化 | 位元 | VRAM | 品質 | 状態 |
|---|---|---|---|---|
| Q2_K | 2 | 38 GB | low | — |
| Q3_K_M | 3 | 52.9 GB | moderate | — |
| Q4_K_M | 4 | 60.4 GB | good | — |
| Q5_K_M | 5 | 75.4 GB | good | — |
| Q6_K | 6 | 90.4 GB | excellent | — |
| Q8_0 | 8 | 120.4 GB | excellent | — |
| F16 | 16 | 240.2 GB | lossless | — |
関于这個模型
Welcome OpenAI’s gpt-oss!
Ollama partners with OpenAI to bring its latest state-of-the-art open weight models to Ollama. The two models, 20B and 120B, bring a whole new local chat experience, and are designed for powerful reasoning, agentic tasks, and versatile developer use cases.
Get started
You can get started by downloading the latest Ollama version.
The model can be downloaded directly in Ollama’s new app or via the terminal:
ollama run gpt-oss:20b
ollama run gpt-oss:120b
Feature highlights
- Agentic capabilities: Use the models’ native capabilities for function calling, web browsing (Ollama is introducing built-in web search that can be optionally enabled), python tool calls, and structured outputs.
- Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs.
- Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
- Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
- Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Quantization - MXFP4 format
OpenAI utilizes quantization to reduce the memory footprint of the gpt-oss models. The models are post-trained with quantization of the mixture-of-experts (MoE) weights to MXFP4 format, where the weights are quantized to 4.25 bits per parameter. The MoE weights are responsible for 90+% of the total parameter count, and quantizing these to MXFP4 enables the smaller model to run on systems with as little as 16GB memory, and the larger model to fit on a single 80GB GPU.
Ollama is supporting the MXFP4 format natively without additional quantizations or conversions. New kernels are developed for Ollama’s new engine to support the MXFP4 format.
Ollama collaborated with OpenAI to benchmark against their reference implementations to ensure Ollama’s implementations have the same quality.
20B parameter model
gpt-oss-20b model is designed for lower latency, local, or specialized use-cases.
120B parameter model
Reference
Can I run GPT-OSS 120B locally?
- Can I run GPT-OSS 120B locally?
- GPT-OSS 120B needs about 65.4 GB of memory at a minimum and 109 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does GPT-OSS 120B need?
- At Q4_K_M, GPT-OSS 120B uses about 60.4 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.