OpenAI GPT OSS 120B Pruned REAP 58B needs about 42.3 GB of memory at Q5_0 (a 41.2 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 41.2 GB (Q5_0) to 63.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 2.4 GB.
OpenAI GPT OSS 120B Pruned REAP 58B is a 59.5B-parameter gpt-oss model in GGUF format, quantized by 12bitmisfit. Its trained context length is 128K tokens. The repository has 2 quant files, from 41.2 GB (Q5_0) to 63.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_0 | 41.2 GB (9 parts) | 42.3 GB | Too big | Get file → | |
| Q8_0 | 63.3 GB (14 parts) | 64.4 GB | Too big | Get file → |
What GPU do you need for OpenAI GPT OSS 120B Pruned REAP 58B?
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: the best quant that fits is Q5_0 (41.2 GB file, about 42.3 GB in use).
Which OpenAI GPT OSS 120B Pruned REAP 58B quant should you choose?
Q5_0 (41.2 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about OpenAI GPT OSS 120B Pruned REAP 58B
How much VRAM does OpenAI GPT OSS 120B Pruned REAP 58B need?
About 42.3 GB at Q5_0 with an 8K context window. That is the 41.2 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 120B Pruned REAP 58B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 42.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of OpenAI GPT OSS 120B Pruned REAP 58B GGUF?
It depends on the quant: Q5_0 is 41.2 GB, Q8_0 is 63.3 GB.
What context length does OpenAI GPT OSS 120B Pruned REAP 58B 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 OpenAI GPT OSS 120B Pruned REAP 58B GGUF?
The files are on Hugging Face in the 12bitmisfit/OpenAI_GPT-OSS-120B_Pruned_REAP_58B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.