Ollama · gpt-oss

![OpenAI gpt-oss banner](/assets/library/gpt-oss/e9da5025-e172-441d-9f06-8dfa797da9b0) ### Welcome OpenAI's gpt-oss! Ollama partners with OpenAI to bring its latest state-of-the-art open weight model…

ollama/gpt-oss

![OpenAI gpt-oss banner](/assets/library/gpt-oss/e9da5025-e172-441d-9f06-8dfa797da9b0)

### 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](https://ollama.com/download).

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.

![benchmark](/assets/library/gpt-oss/d29a500d-303f-4d24-b557-a8247d17ed4c)

### 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](/assets/library/gpt-oss/343d558d-a3bc-472e-9956-37fdc3cc4f6c)

gpt-oss-20b model is designed for lower latency, local, or specialized use-cases.

### 120B parameter model

![gpt-oss 120B](/assets/library/gpt-oss/51b69d33-c747-4117-ba76-a6efa1b0a986)

### Reference

- [OpenAI launch blog](https://openai.com/index/introducing-gpt-oss) - [OpenAI model card](https://openai.com/index/gpt-oss-model-card/) - [NVIDIA RTX blog](https://blogs.nvidia.com/blog/rtx-ai-garage-openai-oss) - [NVIDIA cloud to edge](https://developer.nvidia.com/blog/delivering-1-5-m-tps-inference-on-nvidia-gb200-nvl72-nvidia-accelerates-openai-gpt-oss-models-from-cloud-to-edge/)

Specifications & capabilities

Published model ID
gpt-oss

Deployments & artifacts

1–7 / 7

ollama

source id
ollama
execution mode
cloud
parameter size
116829156672
parameter count
116829156672
parameter count is approximate
false
quantization level
MXFP4
context window
131072
context window is approximate
false
artifact size bytes
65290180781
architecture
gptoss
thinking
values
  • low
  • medium
  • high
default
medium
updated at
2026-11-16T08:10:06.079865+00:00
Confirmed base model
openai/gpt-oss-120b

ollama

source id
ollama
execution mode
cloud
parameter size
20914757184
parameter count
20914757184
parameter count is approximate
false
quantization level
MXFP4
context window
131072
context window is approximate
false
artifact size bytes
13780162412
architecture
gptoss
thinking
values
  • low
  • medium
  • high
default
medium
updated at
2026-11-16T08:10:06.079865+00:00
Confirmed base model
openai/gpt-oss-20b

ollama

source id
ollama
execution mode
local
parameter size
116.8B
parameter count
116800000000
parameter count is approximate
true
quantization level
MXFP4
context window
128000
context window is approximate
true
artifact size bytes
65369819443
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
cloud
parameter size
117B
parameter count
116829156672
parameter count is approximate
false
quantization level
MXFP4
context window
131072
context window is approximate
false
architecture
gptoss
thinking
values
  • low
  • medium
  • high
default
medium
updated at
2026-11-16T08:10:06.079865+00:00
metadata warning
Registry digest differs from the catalog hint. Both observations are retained; representation or tag revision may differ.

ollama

source id
ollama
execution mode
local
parameter size
20.9B
parameter count
20900000000
parameter count is approximate
true
quantization level
MXFP4
context window
128000
context window is approximate
true
artifact size bytes
13793441427
updated at
2026-11-16T08:10:06.079865+00:00

ollama

source id
ollama
execution mode
cloud
parameter size
20.9B
parameter count
20914757184
parameter count is approximate
false
quantization level
MXFP4
context window
131072
context window is approximate
false
architecture
gptoss
thinking
values
  • low
  • medium
  • high
default
medium
updated at
2026-11-16T08:10:06.079865+00:00
metadata warning
Registry digest differs from the catalog hint. Both observations are retained; representation or tag revision may differ.

ollama

source id
ollama
execution mode
local
parameter size
20.9B
parameter count
20900000000
parameter count is approximate
true
quantization level
MXFP4
context window
128000
context window is approximate
true
artifact size bytes
13793441427
updated at
2026-11-16T08:10:06.079865+00:00

Original sources

1–2 / 2

Ollama · Model page ↗

Ollama · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace