Store › model › LLM
gpt-oss-20b-GGUF
by unsloth · source Hugging Face · updated 2025-12-19
apache-2.011 GB~13 GB RAMsource aliveunlabeled
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.
Add to LogiShell Open in the web IDE
The button opens LogiShell with this card; nothing installs from a link by itself. Inside the app the install goes through lsh models install hf:unsloth/gpt-oss-20b-GGUF and its progress lives in the Resource Center.
Source and license
- Source: https://huggingface.co/unsloth/gpt-oss-20b-GGUF
- License: apache-2.0
- Requirements: about 13 GB of RAM, 11 GB on disk (estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models). Runs with llama.cpp, ollama.
- Tags:
transformersggufgpt_osstext-generationopenaiunslothendpoints_compatibleconversational
Numbers
- 490,693 downloads on Hugging Face
- 849 likes
- license apache-2.0
- 11 GB for gpt-oss-20b-Q4_K_M.gguf
- 130,156 stars on ggml-org/llama.cpp
- 2,528 open issues and PRs
- last release v0.5.0 on 2026-09-23
- 327,838 npm downloads a week for node-llama-cpp
- latest node-llama-cpp@3.22.1
Numbers as of 2026-10-02 20:53 UTC, from the source API.
Summary
Summary not ready yet: the numbers are here, the text is not. It is written by the collector through the LogiShell model facade when a provider key is present.
Reviews
No reviews yet. Reviews are written inside LogiShell: open this card in the app.
Files
| file | quant | size |
|---|---|---|
gpt-oss-20b-F16.gguf | F16 | 13 GB |
gpt-oss-20b-Q2_K.gguf | Q2_K | 11 GB |
gpt-oss-20b-Q2_K_L.gguf | Q2_K_L | 11 GB |
gpt-oss-20b-Q3_K_M.gguf | Q3_K_M | 11 GB |
gpt-oss-20b-Q3_K_S.gguf | Q3_K_S | 11 GB |
gpt-oss-20b-Q4_0.gguf | Q4_0 | 11 GB |
gpt-oss-20b-Q4_1.gguf | Q4_1 | 11 GB |
gpt-oss-20b-Q4_K_M.gguf | Q4_K_M | 11 GB |
gpt-oss-20b-Q4_K_S.gguf | Q4_K_S | 11 GB |
gpt-oss-20b-Q5_K_M.gguf | Q5_K_M | 11 GB |
gpt-oss-20b-Q5_K_S.gguf | Q5_K_S | 11 GB |
gpt-oss-20b-Q6_K.gguf | Q6_K | 11 GB |
gpt-oss-20b-Q8_0.gguf | Q8_0 | 11 GB |
gpt-oss-20b-UD-Q4_K_XL.gguf | Q4_K_XL | 11 GB |
gpt-oss-20b-UD-Q6_K_XL.gguf | Q6_K_XL | 11 GB |
gpt-oss-20b-UD-Q8_K_XL.gguf | Q8_K_XL | 12 GB |
From the source README
Read our How to Run gpt-oss Guide here!
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!
- Fine-tune gpt-oss-20b for free using our Google Colab notebook-Fine-tuning.ipynb)
- Read our Blog about gpt-oss support: unsloth.ai/blog/gpt-oss
- View the rest of our notebooks in our docs here.
- Thank you to the 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.
gpt-oss-20b Details
Try gpt-oss ·
Guides ·
System card ·
OpenAI blog
Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.
We’re releasing two flavors of the open models:
- `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fits into a single H100 GPU (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`](https://huggi…
Source: https://huggingface.co/unsloth/gpt-oss-20b-GGUF
Card id model:hf:unsloth/gpt-oss-20b-GGUF · collected 2026-10-02 20:53 UTC · JSON