undermaintenance 118b gpt faulty needs about 89.0 GB of memory at Q4_K_M (a 87.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 4 quants, from 67.0 GB (IQ4_XS) to 233.8 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
undermaintenance 118b gpt faulty is a 117B-parameter gpt-oss model in GGUF format, quantized by ZERO-POINT-AI. Its trained context length is 128K tokens. The repository has 4 quant files, from 67.0 GB (IQ4_XS) to 233.8 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 67.0 GB | 68.1 GB | Too big | Get file → | |
| Q4_K_M | 87.9 GB | 89.0 GB | Too big | Get file → | |
| Q5_K_M | 93.9 GB | 95.0 GB | Too big | Get file → | |
| BF16 | 233.8 GB | 234.9 GB | Too big | Get file → |
What GPU do you need for undermaintenance 118b gpt faulty?
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: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: no quant fits at an 8K context.
Which undermaintenance 118b gpt faulty quant should you choose?
Q4_K_M is the usual starting point for undermaintenance 118b gpt faulty: it balances file size and quality well. Here it is a 87.9 GB file.
If memory is tight, the smallest file is IQ4_XS at 67.0 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 undermaintenance 118b gpt faulty
How much VRAM does undermaintenance 118b gpt faulty need?
About 89.0 GB at Q4_K_M with an 8K context window. That is the 87.9 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 undermaintenance 118b gpt faulty on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 68.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of undermaintenance 118b gpt faulty GGUF?
It depends on the quant: IQ4_XS is 67.0 GB, Q4_K_M is 87.9 GB, Q5_K_M is 93.9 GB, BF16 is 233.8 GB.
What context length does undermaintenance 118b gpt faulty support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.6 GB at 8K and 2.4 GB at 32K.
Where can I download undermaintenance 118b gpt faulty GGUF?
The files are on Hugging Face in the ZERO-POINT-AI/undermaintenance__118b-gpt-faulty repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does undermaintenance 118b gpt faulty 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.