fauxpaslife/gpt-oss-20B-Q5_K_M

fauxpaslife/ gpt-oss-20B-Q5_K_M

150 Downloads Updated 2 weeks ago

12GB Version of GPT-OSS:20B via Unsloth for a slightly smaller footprint with minimal quality loss.

tools thinking

ollama run fauxpaslife/gpt-oss-20B-Q5_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "fauxpaslife/gpt-oss-20B-Q5_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='fauxpaslife/gpt-oss-20B-Q5_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'fauxpaslife/gpt-oss-20B-Q5_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model fauxpaslife/gpt-oss-20B-Q5_K_M

OpenCode

OpenCode ollama launch opencode --model fauxpaslife/gpt-oss-20B-Q5_K_M

Hermes Agent

Hermes Agent ollama launch hermes --model fauxpaslife/gpt-oss-20B-Q5_K_M

OpenClaw

OpenClaw ollama launch openclaw --model fauxpaslife/gpt-oss-20B-Q5_K_M

Models

Name

1 model

Size / Usage

Context

Input

gpt-oss-20B-Q5_K_M:latest

12GB · 128K context window · Text · 2 weeks ago

gpt-oss-20B-Q5_K_M:latest

12GB

128K

Text

Readme

New * Report bugs or version requests.

🦥

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.

Original GGUF: https://huggingface.co/unsloth/gpt-oss-20b-GGUF
Great documentation: https://unsloth.ai/docs/models/gpt-oss-how-to-run-and-fine-tune
About the OpenAI weights: https://openai.com/open-models

This model card is dedicated to the smaller gpt-oss-20b model.

Highlights

- 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.
-Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.

* **New** * [Report bugs or version requests](https://docs.google.com/forms/d/e/1FAIpQLScG4c1UAnXW-jG7Sxv4ExFsk4bTb-uf_Pl9MtEz3iATAloR4w/viewform?usp=dialog).

![Screenshot 2026-09-26 105806.png](/assets/fauxpaslife/gpt-oss-20B-Q5_K_M/fa3a5287-95fd-467c-88bc-5b5e79ef2d38)
![simages.jpg](/assets/fauxpaslife/gpt-oss-20B-Q5_K_M/e529bcae-86a5-4471-a8c8-4eef54628e13)

### 🦥

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.

**Original GGUF**: https://huggingface.co/unsloth/gpt-oss-20b-GGUF <br>
**Great documentation**: https://unsloth.ai/docs/models/gpt-oss-how-to-run-and-fine-tune <br>
**About the OpenAI weights**: https://openai.com/open-models <br>

This model card is dedicated to the smaller gpt-oss-20b model.
**Highlights**

- 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.
    -Native MXFP4 quantization: The models are trained with native MXFP4 precision for the MoE layer, making gpt-oss-120b run on a single H100 GPU and the gpt-oss-20b model run within 16GB of memory.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)