Big Gpt Oss needs about 149.5 GB of memory at Q4_K_M (a 147.9 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 10 quants, from 106.5 GB (MXFP4_MOE) to 158.3 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 4.1 GB.
Big Gpt Oss is a 197B-parameter gpt-oss model in GGUF format, quantized by mradermacher. Its trained context length is 128K tokens. The repository has 10 quant files, from 106.5 GB (MXFP4_MOE) to 158.3 GB (Q5_K_M).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4_MOE | 106.5 GB | 108.1 GB | Too big | Get file → | |
| Q3_K_S | 111.4 GB | 112.9 GB | Too big | Get file → | |
| Q2_K | 111.4 GB | 113.0 GB | Too big | Get file → | |
| IQ4_XS | 112.9 GB | 114.4 GB | Too big | Get file → | |
| Q3_K_M | 119.8 GB | 121.3 GB | Too big | Get file → | |
| Q3_K_L | 123.8 GB | 125.3 GB | Too big | Get file → | |
| Q4_K_S | 136.5 GB | 138.0 GB | Too big | Get file → | |
| Q4_K_M | 147.9 GB | 149.5 GB | Too big | Get file → | |
| Q5_K_S | 148.3 GB | 149.8 GB | Too big | Get file → | |
| Q5_K_M | 158.3 GB | 159.8 GB | Too big | Get file → |
What GPU do you need for Big Gpt Oss?
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 Big Gpt Oss quant should you choose?
Q4_K_M is the usual starting point for Big Gpt Oss: it balances file size and quality well. Here it is a 147.9 GB file.
If memory is tight, the smallest file is MXFP4_MOE at 106.5 GB, with the quality trade-offs that come with fewer bits. 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 Big Gpt Oss
How much VRAM does Big Gpt Oss need?
About 149.5 GB at Q4_K_M with an 8K context window. That is the 147.9 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 Big Gpt Oss on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 108.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Big Gpt Oss GGUF?
It depends on the quant: MXFP4_MOE is 106.5 GB, Q3_K_S is 111.4 GB, Q2_K is 111.4 GB, IQ4_XS is 112.9 GB, Q3_K_M is 119.8 GB, Q3_K_L is 123.8 GB and 4 more.
What context length does Big Gpt Oss support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.0 GB at 8K and 4.1 GB at 32K.
Where can I download Big Gpt Oss GGUF?
The files are on Hugging Face in the mradermacher/big-gpt-oss-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.