OpenAi GPT Oss 36B BrainStorm20x Uncensored needs about 28.7 GB of memory at Q4_K_M (a 27.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.1 GB to 38.8 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 2.9 GB.
36B parameter GPT‑OSS model with BrainStorm20x adapter
OpenAi GPT‑OSS 36B BrainStorm20x Uncensored is a 36.6B parameter model trained on 131072 context tokens. It supports coding and reasoning tasks and is released under the apache‑2.0 license.
Good at
- Coding
- Reasoning
- Uncensored content generation
Limits
- Large VRAM requirement for full precision
- No vision support
- Requires careful prompting for explicit content
Best for
- Developers building coding assistants
- Researchers testing large‑context reasoning
- Users needing uncensored text generation
Who it’s for. This model is suitable for developers and researchers who need a large, uncensored language model with strong coding and reasoning abilities. It is ideal for those who can provide the necessary GPU memory and are comfortable managing prompt direction for explicit content.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 1.3 GB | Fits | Get file → | |
| IQ1_M | 20.8 GB | 22.0 GB | Too big | Get file → | |
| IQ1_S | 20.8 GB | 22.0 GB | Too big | Get file → | |
| IQ2_XXS | 20.8 GB | 22.0 GB | Too big | Get file → | |
| IQ2_XS | 20.8 GB | 22.0 GB | Too big | Get file → | |
| Q3_K_S | 20.9 GB | 22.1 GB | Too big | Get file → | |
| IQ2_M | 20.9 GB | 22.1 GB | Too big | Get file → | |
| IQ2_S | 20.9 GB | 22.1 GB | Too big | Get file → | |
| IQ3_S | 20.9 GB | 22.1 GB | Too big | Get file → | |
| IQ3_XS | 20.9 GB | 22.1 GB | Too big | Get file → | |
| IQ3_XXS | 20.9 GB | 22.1 GB | Too big | Get file → | |
| Q2_K | 20.9 GB | 22.1 GB | Too big | Get file → | |
| IQ4_XS | 20.9 GB | 22.1 GB | Too big | Get file → | |
| Q2_K_S | 21.0 GB | 22.2 GB | Too big | Get file → | |
| Q4_0 | 21.0 GB | 22.2 GB | Too big | Get file → | |
| IQ3_M | 21.1 GB | 22.3 GB | Too big | Get file → | |
| Q3_K_M | 22.4 GB | 23.6 GB | Too big | Get file → | |
| Q3_K_L | 23.1 GB | 24.4 GB | Too big | Get file → | |
| Q4_1 | 23.2 GB | 24.4 GB | Too big | Get file → | |
| Q4_K_S | 25.4 GB | 26.7 GB | Too big | Get file → | |
| Q4_K_M | 27.5 GB | 28.7 GB | Too big | Get file → | |
| Q5_K_S | 27.6 GB | 28.9 GB | Too big | Get file → | |
| Q5_K_M | 29.4 GB | 30.6 GB | Too big | Get file → | |
| Q6_K | 38.8 GB | 40.0 GB | Too big | Get file → |
For 8‑GB VRAM, use the IQ1_M or IQ1_S quant, each about 20.77 GB file size and 22 GB memory at 8K context. For 16‑GB VRAM, consider Q2_K or Q3_K_S, around 20.86–25.44 GB file size and 22–26.7 GB memory. For 24‑GB VRAM, Q4_K_M or Q5_K_M offer 27.45–29.38 GB file size and 28.7–30.6 GB memory. Estimates are approximate.
What GPU do you need for OpenAi GPT Oss 36B BrainStorm20x Uncensored?
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 (0.1 GB file, about 1.3 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q3_K_M (22.4 GB file, about 23.6 GB in use).
- 32 GB VRAM: the best quant that fits is Q5_K_M (29.4 GB file, about 30.6 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.8 GB file, about 40.0 GB in use).
Which OpenAi GPT Oss 36B BrainStorm20x Uncensored quant should you choose?
Q4_K_M is the usual starting point for OpenAi GPT Oss 36B BrainStorm20x Uncensored: it balances file size and quality well. Here it is a 27.5 GB file.
If memory is tight, the smallest file is the first one in the table at 0.1 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 OpenAi GPT Oss 36B BrainStorm20x Uncensored
How much VRAM does OpenAi GPT Oss 36B BrainStorm20x Uncensored need?
About 28.7 GB at Q4_K_M with an 8K context window. That is the 27.5 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 OpenAi GPT Oss 36B BrainStorm20x Uncensored on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 1.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of OpenAi GPT Oss 36B BrainStorm20x Uncensored GGUF?
It depends on the quant: file is 0.1 GB, IQ1_M is 20.8 GB, IQ1_S is 20.8 GB, IQ2_XXS is 20.8 GB, IQ2_XS is 20.8 GB, Q3_K_S is 20.9 GB and 18 more.
What context length does OpenAi GPT Oss 36B BrainStorm20x Uncensored support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.7 GB at 8K and 2.9 GB at 32K.
Where can I download OpenAi GPT Oss 36B BrainStorm20x Uncensored GGUF?
The files are on Hugging Face in the mradermacher/OpenAi-GPT-oss-36B-BrainStorm20x-uncensored-i1-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 OpenAi GPT Oss 36B BrainStorm20x Uncensored 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 IQ1_M or IQ1_S quant; each requires about 22 GB memory at 8K context, so 8 GB VRAM is insufficient.
Does this model support image inputs?
No, the model has no vision capabilities.
What license applies to this model?
The model is released under the apache‑2.0 license.