ggml org gpt oss 20b GGUF SPLIT needs about 13.0 GB of memory at its main file (a 12.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.
ggml org gpt oss 20b GGUF SPLIT is a 20.9B-parameter gpt-oss model in GGUF format, quantized by DanyDA. Its trained context length is 128K tokens. The repository has 1 quant file, from 12.1 GB to 12.1 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 12.1 GB (3 parts) | 13.0 GB | Too big | Get file → |
What GPU do you need for ggml org gpt oss 20b GGUF SPLIT?
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: the best quant that fits is the main file (12.1 GB file, about 13.0 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ggml org gpt oss 20b GGUF SPLIT
How much VRAM does ggml org gpt oss 20b GGUF SPLIT need?
About 13.0 GB at its main file with an 8K context window. That is the 12.1 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 ggml org gpt oss 20b GGUF SPLIT on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of ggml org gpt oss 20b GGUF SPLIT GGUF?
It depends on the quant: file is 12.1 GB.
What context length does ggml org gpt oss 20b GGUF SPLIT support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.
Where can I download ggml org gpt oss 20b GGUF SPLIT GGUF?
The files are on Hugging Face in the DanyDA/ggml-org-gpt-oss-20b-GGUF-SPLIT repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.