gpt-oss-20b-heretic needs about 16.9 GB of memory at Q4_K_M (a 16.0 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 0.0 GB to 41.9 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
gpt-oss-20b-heretic: 20.9B parameter MoE model in GGUF format
gpt-oss-20b-heretic is a 20.9B parameter mixture of experts model. It supports 131072 token context and is released under Apache‑2.0. The model is available in multiple quantizations for different memory budgets.
Good at
- Tool‑based reasoning
- Agentic task execution
- Large context handling
Limits
- No vision support
- Requires harmony format
- Large VRAM needed for higher precision
Best for
- Local inference on high‑VRAM GPUs
- Developer prototyping of agentic workflows
- Testing quantization strategies
Who it’s for. Engineers and researchers who need a large MoE model for local inference. The model is suitable for developers building agentic applications and for those experimenting with custom quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 0.9 GB | Fits | Get file → | |
| IQ4_NL | 11.8 GB | 12.7 GB | Too big | Get file → | |
| IQ1_S | 11.9 GB | 12.8 GB | Too big | Get file → | |
| IQ2_XXS | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ1_M | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ2_XS | 12.0 GB | 12.9 GB | Too big | Get file → | |
| Q2_K_M | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ2_M | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ2_S | 12.0 GB | 12.9 GB | Too big | Get file → | |
| Q2_K_S | 12.0 GB | 12.9 GB | Too big | Get file → | |
| Q3_K_S | 12.0 GB | 12.9 GB | Too big | Get file → | |
| IQ3_XS | 12.4 GB | 13.3 GB | Too big | Get file → | |
| IQ3_XXS | 12.4 GB | 13.3 GB | Too big | Get file → | |
| IQ4_XS | 12.4 GB | 13.3 GB | Too big | Get file → | |
| Q4_0 | 12.4 GB | 13.3 GB | Too big | Get file → | |
| IQ3_M | 12.5 GB | 13.4 GB | Too big | Get file → | |
| Q4_1 | 13.2 GB | 14.1 GB | Too big | Get file → | |
| Q3_K_M | 13.2 GB | 14.1 GB | Too big | Get file → | |
| Q5_0 | 14.9 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_S | 14.9 GB | 15.8 GB | Too big | Get file → | |
| Q4_K_M | 16.0 GB | 16.9 GB | Too big | Get file → | |
| Q5_1 | 16.1 GB | 17.0 GB | Too big | Get file → | |
| Q5_K_M | 17.1 GB | 18.0 GB | Too big | Get file → | |
| Q6_K_M | 22.2 GB | 23.1 GB | Too big | Get file → | |
| Q8_0 | 22.3 GB | 23.2 GB | Too big | Get file → | |
| F16 | 23.6 GB | 24.5 GB | Too big | Get file → | |
| BF16 | 41.9 GB | 42.8 GB | Too big | Get file → |
For 8‑GB VRAM use IQ4_NL (12.7 GB memory at 8k context). For 12‑GB VRAM use Q4_0 (13.3 GB). For 16‑GB VRAM use Q4_K_M (16.9 GB). Memory estimates are approximate.
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: 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 Q4_K_S (14.9 GB file, about 15.8 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 GB in use).
- 32 GB VRAM: the best quant that fits is F16 (23.6 GB file, about 24.5 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (41.9 GB file, about 42.8 GB in use).
Which gpt-oss-20b-heretic quant should you choose?
Q4_K_M is the usual starting point for gpt-oss-20b-heretic: it balances file size and quality well. Here it is a 16.0 GB file.
The Q8_0 file is 22.3 GB, about 1.4 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-heretic
How much VRAM does gpt-oss-20b-heretic need?
About 16.9 GB at Q4_K_M with an 8K context window. That is the 16.0 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?
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-heretic GGUF?
It depends on the quant: file is 0.0 GB, IQ4_NL is 11.8 GB, IQ1_S is 11.9 GB, IQ2_XXS is 12.0 GB, IQ1_M is 12.0 GB, IQ2_XS is 12.0 GB and 21 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 Mungert/gpt-oss-20b-heretic-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 gpt-oss-20b-heretic on 8 GB VRAM?
Use the IQ4_NL quantization; it requires about 12.7 GB memory at 8k context, which is close to 8 GB but may need swapping.
Does the model support vision tasks?
No, the model has no vision capability.
What license applies to this model?
The model is released under the Apache‑2.0 license.