gpt oss puzzle 88B needs about 49.2 GB of memory at MXFP4_MOE (a 48.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 2 quants, from 48.1 GB (MXFP4_MOE) to 50.1 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
gpt oss puzzle 88B is a 88.2B-parameter gpt-oss model in GGUF format, quantized by SamPurkis. Its trained context length is 224K tokens. The repository has 2 quant files, from 48.1 GB (MXFP4_MOE) to 50.1 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 48.1 GB | 49.2 GB | Too big | Get file → | |
| F16 | 50.1 GB | 51.2 GB | Too big | Get file → |
What GPU do you need for gpt oss puzzle 88B?
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 gpt oss puzzle 88B quant should you choose?
MXFP4_MOE (48.1 GB) is the middle option in this repository. Lower bit counts mean smaller files and more quality loss.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gpt oss puzzle 88B
How much VRAM does gpt oss puzzle 88B need?
About 49.2 GB at MXFP4_MOE with an 8K context window. That is the 48.1 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 puzzle 88B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 49.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of gpt oss puzzle 88B GGUF?
It depends on the quant: MXFP4_MOE is 48.1 GB, F16 is 50.1 GB.
What context length does gpt oss puzzle 88B support?
The GGUF header lists a trained context length of 229,376 tokens (224K). 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 gpt oss puzzle 88B GGUF?
The files are on Hugging Face in the SamPurkis/gpt-oss-puzzle-88B-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 puzzle 88B use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.