Gpt Oss 20b Heretic needs about 16.6 GB of memory at Q5_1 (a 15.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 17 quants, from 11.8 GB (IQ4_NL) to 22.1 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
20.9B‑parameter GPT‑OSS MOE model with uncensored output
Gpt Oss 20b Heretic is a 20.9B‑parameter GPT‑OSS model with a mixture of experts. It is trained on 131072 context tokens and licensed under Apache‑2.0. The model supports coding, reasoning, and tool usage.
Good at
- Coding and code generation
- Complex reasoning tasks
- Tool‑based interactions
Limits
- No vision support
- Requires harmony response format
- Large memory footprint for higher quantizations
Best for
- Local LLM deployment on GPUs with 16GB VRAM
- Fine‑tuning for specialized tasks
- Agentic workflows with function calling
Who it’s for. Developers and researchers who need a large, uncensored GPT‑OSS model for local inference or fine‑tuning. The Apache‑2.0 license allows commercial use without copyleft restrictions.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| IQ4_NL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| IQ4_NL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| IQ4_NL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| IQ4_NL | 12.6 GB | 13.6 GB | Too big | Get file → | |
| IQ4_NL | 12.6 GB | 13.6 GB | Too big | Get file → | |
| Q5_1 | 15.7 GB | 16.6 GB | Too big | Get file → | |
| Q5_1 | 15.7 GB | 16.6 GB | Too big | Get file → | |
| Q5_1 | 15.7 GB | 16.6 GB | Too big | Get file → | |
| Q5_1 | 15.7 GB | 16.6 GB | Too big | Get file → | |
| Q5_1 | 15.7 GB | 16.6 GB | Too big | Get file → | |
| Q5_1 | 16.5 GB | 17.4 GB | Too big | Get file → | |
| Q8_0 | 22.0 GB | 22.9 GB | Too big | Get file → | |
| Q8_0 | 22.1 GB | 23.0 GB | Too big | Get file → | |
| Q8_0 | 22.1 GB | 23.0 GB | Too big | Get file → | |
| Q8_0 | 22.1 GB | 23.0 GB | Too big | Get file → | |
| Q8_0 | 22.1 GB | 23.0 GB | Too big | Get file → |
For 8GB VRAM, use IQ4_NL (file size 11.82 GB, estimated 12.7 GB memory). For 16GB VRAM, Q5_1 (15.73 GB, 16.6 GB memory) or IQ4_NL (12.65 GB, 13.6 GB memory) are suitable. For 24GB VRAM, Q8_0 (21.97 GB, 22.9 GB memory) can be used.
What GPU do you need for Gpt Oss 20b Heretic?
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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is IQ4_NL (12.6 GB file, about 13.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (22.1 GB file, about 23.0 GB in use).
Which Gpt Oss 20b Heretic quant should you choose?
Q5_1 (15.7 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is IQ4_NL at 11.8 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Gpt Oss 20b Heretic
How much VRAM does Gpt Oss 20b Heretic need?
About 16.6 GB at Q5_1 with an 8K context window. That is the 15.7 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 Heretic on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 12.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Gpt Oss 20b Heretic GGUF?
It depends on the quant: IQ4_NL is 11.8 GB, IQ4_NL is 11.8 GB, IQ4_NL is 11.8 GB, IQ4_NL is 11.8 GB, IQ4_NL is 12.6 GB, IQ4_NL is 12.6 GB and 11 more.
What context length does Gpt Oss 20b Heretic 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 Heretic GGUF?
The files are on Hugging Face in the botp/OpenAi-GPT-oss-20b-HERETIC-uncensored-NEO-Imatrix-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 Heretic 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 this model on 8 GB VRAM?
Yes, the IQ4_NL quantization requires about 12.7 GB memory at 8k context, which fits on an 8 GB VRAM GPU with some swapping.
Does the model support vision inputs?
No, the model has no vision capability and only processes text.
What license applies to this model?
The model is released under the Apache‑2.0 license, allowing free use and modification.