gpt-oss-120b — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
gpt-oss-20b — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)

Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.

[!NOTE] This model card is dedicated to the smaller gpt-oss-20b model. Check out gpt-oss-120b for the larger model.

Highlight

Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
Full chain-of-thought: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in outputs. It’s not intended to be shown to end users.
Fine-tunable: Fully customize models to your specific use case through parameter fine-tuning.
Agentic capabilities: Use the models’ native capabilities for function calling, web browsing, Python code execution, and Structured Outputs.
MXFP4 quantization: The models were post-trained with MXFP4 quantization of the MoE weights, making gpt-oss-120b run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the gpt-oss-20b model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.

Inference examples

Transformers

You can use gpt-oss-120b and gpt-oss-20b with Transformers. If you use the Transformers chat template, it will automatically apply the harmony response format. If you use model.generate directly, you need to apply the harmony format manually using the chat template or use our openai-harmony package.

To get started, install the necessary dependencies to setup your environment:

pip install -U transformers kernels torch

Once, setup you can proceed to run the model by running the snippet below:

from transformers import pipeline
import torch
model_id = "openai/gpt-oss-20b"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype="auto",
    device_map="auto",
)
messages = [
    {"role": "user", "content": "Explain quantum mechanics clearly and concisely."},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

Alternatively, you can run the model via Transformers Serve to spin up a OpenAI-compatible webserver:

transformers serve
transformers chat localhost:8000 --model-name-or-path openai/gpt-oss-20b

Learn more about how to use gpt-oss with Transformers.

Unsloth

Installation

%%capture
# We're installing the latest Torch, Triton, OpenAI's Triton kernels, Transformers and Unsloth!
!pip install --upgrade -qqq uv
try: import numpy; install_numpy = f"numpy=={numpy.__version__}"
except: install_numpy = "numpy"
!uv pip install -qqq \
    "torch>=2.8.0" "triton>=3.4.0" {install_numpy} \
    "unsloth_zoo[base] @ git+https://github.com/unslothai/unsloth-zoo" \
    "unsloth[base] @ git+https://github.com/unslothai/unsloth" \
    torchvision bitsandbytes \
    git+https://github.com/huggingface/transformers \
    git+https://github.com/triton-lang/triton.git@05b2c186c1b6c9a08375389d5efe9cb4c401c075#subdirectory=python/triton_kernels

Loading model

from unsloth import FastLanguageModel
import torch
max_seq_length = 1024
dtype = None
# 4bit pre quantized models we support for 4x faster downloading + no OOMs.
fourbit_models = [
    "unsloth/gpt-oss-20b-unsloth-bnb-4bit", # 20B model using bitsandbytes 4bit quantization
    "unsloth/gpt-oss-120b-unsloth-bnb-4bit",
    "unsloth/gpt-oss-20b", # 20B model using MXFP4 format
    "unsloth/gpt-oss-120b",
] # More models at https://huggingface.co/unsloth
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "EpistemeAI/gpt-oss-20b-unsloth-finetune-lora",
    dtype = dtype, # None for auto detection
    max_seq_length = max_seq_length, # Choose any for long context!
    load_in_4bit = True,  # 4 bit quantization to reduce memory
    full_finetuning = False, # [NEW!] We have full finetuning now!
    # token = "hf_...", # use one if using gated models
)

Lora adapter

model = FastLanguageModel.get_peft_model(
    model,
    r = 8, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128
    target_modules = ["q_proj", "k_proj", "v_proj", "o_proj",
                      "gate_proj", "up_proj", "down_proj",],
    lora_alpha = 16,
    lora_dropout = 0, # Supports any, but = 0 is optimized
    bias = "none",    # Supports any, but = "none" is optimized
    # [NEW] "unsloth" uses 30% less VRAM, fits 2x larger batch sizes!
    use_gradient_checkpointing = "unsloth", # True or "unsloth" for very long context
    random_state = 3407,
    use_rslora = False,  # We support rank stabilized LoRA
    loftq_config = None, # And LoftQ
)

You can use unsloth message example:

messages = [
    {"role": "system", "content": "You are a helpful assistant that can solve puzzle problems."},
    {"role": "user", "content": "Solve x^5 + 3x^4 - 10 = 3."},
]
inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt = True,
    return_tensors = "pt",
    return_dict = True,
    reasoning_effort = "high", # **NEW!** Set reasoning effort to low, medium or high
).to(model.device)
_ = model.generate(**inputs, max_new_tokens = 64, streamer = TextStreamer(tokenizer))

vLLM

vLLM recommends using uv for Python dependency management. You can use vLLM to spin up an OpenAI-compatible webserver. The following command will automatically download the model and start the server.

bash

uv pip install --pre vllm==0.10.1+gptoss \
    --extra-index-url https://wheels.vllm.ai/gpt-oss/ \
    --extra-index-url https://download.pytorch.org/whl/nightly/cu128 \
    --index-strategy unsafe-best-match
vllm serve openai/gpt-oss-20b

Learn more about how to use gpt-oss with vLLM.

PyTorch / Triton

To learn about how to use this model with PyTorch and Triton, check out our reference implementations in the gpt-oss repository.

Ollama

If you are trying to run gpt-oss on consumer hardware, you can use Ollama by running the following commands after installing Ollama.

bash

# gpt-oss-20b
ollama pull gpt-oss:20b
ollama run gpt-oss:20b

Learn more about how to use gpt-oss with Ollama.

LM Studio

If you are using LM Studio you can use the following commands to download.

bash

# gpt-oss-20b
lms get openai/gpt-oss-20b

Check out our awesome list for a broader collection of gpt-oss resources and inference partners.

Download the model

You can download the model weights from the Hugging Face Hub directly from Hugging Face CLI:

shell

# gpt-oss-20b
huggingface-cli download openai/gpt-oss-20b --include "original/*" --local-dir gpt-oss-20b/
pip install gpt-oss
python -m gpt_oss.chat model/

Reasoning levels

You can adjust the reasoning level that suits your task across three levels:

Low: Fast responses for general dialogue.
Medium: Balanced speed and detail.
High: Deep and detailed analysis.

The reasoning level can be set in the system prompts, e.g., "Reasoning: high".

Tool use

The gpt-oss models are excellent for:

Web browsing (using built-in browsing tools)
Function calling with defined schemas
Agentic operations like browser tasks

Fine-tuning

Both gpt-oss models can be fine-tuned for a variety of specialized use cases.

This smaller model gpt-oss-20b can be fine-tuned on consumer hardware, whereas the larger gpt-oss-120b can be fine-tuned on a single H100 node.

See our collection for all versions of gpt-oss including GGUF, 4-bit & 16-bit formats.

Learn to run gpt-oss correctly - Read our Guide.

See Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.

✨ Read our gpt-oss Guide here!

- Read our Blog about gpt-oss support: [unsloth.ai/blog/gpt-oss](https://unsloth.ai/blog/gpt-oss) - View the rest of our notebooks in our [docs here](https://docs.unsloth.ai/get-started/unsloth-notebooks). - Thank you to the [llama.cpp](https://github.com/ggml-org/llama.cpp) team for their work on supporting this model. We wouldn't be able to release quants without them! The F32 quant is MXFP4 upcasted to BF16 for every single layer and is unquantized.

Uploaded model

Developed by: EpistemeAI
License: apache-2.0
Finetuned from model : unsloth/gpt-oss-20b-unsloth-bnb-4bit

This gpt_oss model was trained 2x faster with Unsloth and Huggingface's TRL library.