Gpt Oss 20b needs about 12.6 GB of memory at Q4_K_M (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 29 quants, from 0.0 GB to 13.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
OpenAI GPT‑OSS 20B, 20 billion‑parameter MoE model for reasoning and agentic tasks
GPT‑OSS 20B is a 20 billion‑parameter mixture‑of‑experts model trained on the harmony response format. It supports chain‑of‑thought reasoning, function calling, web browsing, Python execution, and structured outputs. The model is released under Apache 2.0 and can be fine‑tuned.
Good at
- Reasoning with chain‑of‑thought
- Agentic function calling
- Fine‑tuning for custom tasks
Limits
- Requires 8 k context for estimates
- Large memory footprint (~13 GB for 8 k context)
- No vision support
Best for
- Local inference on 16 GB GPUs
- Fine‑tuning for specialized applications
- Developing agentic workflows
Who it’s for. Developers and researchers needing a large, open‑weight model for reasoning and agentic tasks. The Apache 2.0 license allows commercial use and customization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_L | 11.5 GB | 12.4 GB | Too big | Get file → | |
| IQ2_XS | 11.5 GB | 12.4 GB | Too big | Get file → | |
| IQ2_XXS | 11.5 GB | 12.4 GB | Too big | Get file → | |
| Q4_0 | 11.5 GB | 12.4 GB | Too big | Get file → | |
| IQ2_M | 11.5 GB | 12.4 GB | Too big | Get file → | |
| IQ2_S | 11.5 GB | 12.4 GB | Too big | Get file → | |
| Q3_K_S | 11.6 GB | 12.5 GB | Too big | Get file → | |
| IQ3_M | 11.6 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XS | 11.6 GB | 12.5 GB | Too big | Get file → | |
| IQ3_XXS | 11.6 GB | 12.5 GB | Too big | Get file → | |
| Q2_K | 11.6 GB | 12.5 GB | Too big | Get file → | |
| Q3_K_M | 11.6 GB | 12.5 GB | Too big | Get file → | |
| IQ4_NL | 11.6 GB | 12.5 GB | Too big | Get file → | |
| IQ4_XS | 11.6 GB | 12.5 GB | Too big | Get file → | |
| Q4_1 | 11.6 GB | 12.5 GB | Too big | Get file → | |
| Q4_K_S | 11.7 GB | 12.6 GB | Too big | Get file → | |
| Q4_K_M | 11.7 GB | 12.6 GB | Too big | Get file → | |
| Q5_K_S | 11.7 GB | 12.6 GB | Too big | Get file → | |
| Q5_K_M | 11.7 GB | 12.6 GB | Too big | Get file → | |
| Q3_K_XL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| Q2_K_L | 11.8 GB | 12.8 GB | Too big | Get file → | |
| Q4_K_L | 11.9 GB | 12.8 GB | Too big | Get file → | |
| Q5_K_L | 11.9 GB | 12.8 GB | Too big | Get file → | |
| Q6_K | 12.0 GB | 12.9 GB | Too big | Get file → | |
| Q6_K_L | 12.0 GB | 12.9 GB | Too big | Get file → | |
| MXFP4 | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q8_0 | 12.1 GB | 13.0 GB | Too big | Get file → | |
| BF16 | 13.8 GB | 14.7 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_0 (≈12.5 GB memory). For 16 GB VRAM, Q4_K_M or Q5_K_M (≈12.6 GB). For 32 GB VRAM, the full‑precision BF16 (≈14.7 GB) gives the best quality.
What GPU do you need for Gpt Oss 20b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 0.9 GB in use).
- 16 GB VRAM: the best quant that fits is BF16 (13.8 GB file, about 14.7 GB in use).
Which Gpt Oss 20b quant should you choose?
Q4_K_M is the usual starting point for Gpt Oss 20b: it balances file size and quality well. Here it is a 11.7 GB file.
The Q8_0 file is 12.1 GB, about 1.0 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt Oss 20b
How much VRAM does Gpt Oss 20b need?
About 12.6 GB at Q4_K_M with an 8K context window. That is the 11.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Gpt Oss 20b on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Gpt Oss 20b GGUF?
It depends on the quant: file is 0.0 GB, Q3_K_L is 11.5 GB, IQ2_XS is 11.5 GB, IQ2_XXS is 11.5 GB, Q4_0 is 11.5 GB, IQ2_M is 11.5 GB and 23 more.
What context length does Gpt Oss 20b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download Gpt Oss 20b GGUF?
The files are on Hugging Face in the bartowski/openai_gpt-oss-20b-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Gpt Oss 20b use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run GPT‑OSS 20B on 8 GB VRAM?
Only the Q4_0 quantization uses about 12.5 GB at 8 k context, so 8 GB VRAM is insufficient for full inference.
Does the model support vision inputs?
No, GPT‑OSS 20B is a text‑only model and does not handle vision data.
Is the model fine‑tunable?
Yes, the model can be fine‑tuned on custom datasets under the Apache 2.0 license.