siro finetune f16 needs about 31.4 GB of memory at F16 (a 29.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
siro finetune f16 is a 14.8B-parameter Siro model in GGUF format, quantized by sesang06. Its trained context length is 40K tokens. The repository has 1 quant file, from 29.5 GB (F16) to 29.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 29.5 GB | 31.4 GB | Too big | Get file → |
What GPU do you need for siro finetune f16?
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: the best quant that fits is F16 (29.5 GB file, about 31.4 GB in use).
Which siro finetune f16 quant should you choose?
F16 (29.5 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about siro finetune f16
How much VRAM does siro finetune f16 need?
About 31.4 GB at F16 with an 8K context window. That is the 29.5 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 siro finetune f16 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 31.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of siro finetune f16 GGUF?
It depends on the quant: F16 is 29.5 GB.
What context length does siro finetune f16 support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download siro finetune f16 GGUF?
The files are on Hugging Face in the sesang06/siro_finetune_f16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.