oss sde finetune needs about 14.1 GB of memory at MXFP4 (a 12.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 2 quants, from 12.1 GB (MXFP4) to 41.9 GB (BF16).
oss sde finetune is a 20.9B-parameter Oss model in GGUF format, quantized by umaraftab174. Its trained context length is 128K tokens. The repository has 2 quant files, from 12.1 GB (MXFP4) to 41.9 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| MXFP4 | 12.1 GB | 14.1 GB | Too big | Get file → | |
| BF16 | 41.9 GB | 47.4 GB | Too big | Get file → |
What GPU do you need for oss sde finetune?
These figures add the file size, an fp16 KV cache at an 8K context window 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 MXFP4 (12.1 GB file, about 14.1 GB in use).
- 24 GB VRAM: the best quant that fits is MXFP4 (12.1 GB file, about 14.1 GB in use).
- 32 GB VRAM: the best quant that fits is MXFP4 (12.1 GB file, about 14.1 GB in use).
- 48 GB VRAM: the best quant that fits is BF16 (41.9 GB file, about 47.4 GB in use).
Which oss sde finetune quant should you choose?
MXFP4 (12.1 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 oss sde finetune
How much VRAM does oss sde finetune need?
About 14.1 GB at MXFP4 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 oss sde finetune on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of oss sde finetune GGUF?
It depends on the quant: MXFP4 is 12.1 GB, BF16 is 41.9 GB.
What context length does oss sde finetune support?
The GGUF header lists a trained context length of 131,072 tokens (128K).
Where can I download oss sde finetune GGUF?
The files are on Hugging Face in the umaraftab174/oss-sde-finetune repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.