Gpt Oss 20b Heretic needs about 16.7 GB of memory at Q4_K_M (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 12.1 GB (Q3_K_S) to 22.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
20.9B parameter GPT‑OSS model with MoE and tool‑calling
Gpt Oss 20b Heretic is a 20.9B‑parameter GPT‑OSS model with a mixture of experts. It supports tool calling and is available under an Apache‑2.0 license. The model is trained on 131072 context tokens and can be used with the harmony response format.
Good at
- Tool calling
- Agentic tasks
- Fine‑tuning
Limits
- No vision support
- Requires harmony format
- Large memory for higher quant
Best for
- Local inference on 16GB GPUs
- Custom agent development
- Fine‑tuning for specialized tasks
Who it’s for. Developers needing a large, open‑weight GPT‑OSS model that supports function calling and agentic capabilities. The model is suitable for local deployment and fine‑tuning under an Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 12.1 GB | 13.0 GB | Too big | Get file → | |
| Q2_K | 12.1 GB | 13.0 GB | Too big | Get file → | |
| MXFP4_MOE | 12.1 GB | 13.0 GB | Too big | Get file → | |
| IQ4_XS | 12.2 GB | 13.1 GB | Too big | Get file → | |
| Q3_K_M | 12.9 GB | 13.8 GB | Too big | Get file → | |
| Q3_K_L | 13.3 GB | 14.2 GB | Too big | Get file → | |
| Q4_K_S | 14.7 GB | 15.6 GB | Too big | Get file → | |
| Q4_K_M | 15.8 GB | 16.7 GB | Too big | Get file → | |
| Q5_K_S | 15.9 GB | 16.8 GB | Too big | Get file → | |
| Q5_K_M | 16.9 GB | 17.8 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 23.1 GB | Too big | Get file → | |
| Q8_0 | 22.3 GB | 23.2 GB | Too big | Get file → |
For 8‑GB VRAM, use Q3_K_S (12.06 GB file, ~13 GB memory at 8K context). For 16‑GB VRAM, Q4_K_S (14.65 GB file, ~15.6 GB memory) or Q4_K_M (15.81 GB file, ~16.7 GB memory). For 24‑GB VRAM, Q5_K_M (16.89 GB file, ~17.8 GB memory) or Q6_K (22.19 GB file, ~23.1 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: 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 Q4_K_S (14.7 GB file, about 15.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (22.3 GB file, about 23.2 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 15.8 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 Q3_K_S at 12.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 16.7 GB at Q4_K_M with an 8K context window. That is the 15.8 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 13.0 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: Q3_K_S is 12.1 GB, Q2_K is 12.1 GB, MXFP4_MOE is 12.1 GB, IQ4_XS is 12.2 GB, Q3_K_M is 12.9 GB, Q3_K_L is 13.3 GB and 6 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 mradermacher/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 this model on 8 GB VRAM?
Use the Q3_K_S quant, which requires about 13 GB of VRAM at 8K context.
Does the model support vision?
No, the model has no vision capabilities.
What license applies?
The model is released under the Apache‑2.0 license.