gemma poc finetune needs about 9.4 GB of memory at BF16 (a 7.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 4.1 GB (Q8_0) to 7.8 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.6 GB.
gemma poc finetune is a 3.88B-parameter Gemma model in GGUF format, quantized by kygbjs. Its trained context length is 128K tokens. The repository has 3 quant files, from 4.1 GB (Q8_0) to 7.8 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 4.1 GB | 5.8 GB | Fits | Get file → | |
| BF16 | 7.8 GB | 9.4 GB | Too big | Get file → | |
| F16 | 7.8 GB | 9.4 GB | Too big | Get file → |
What GPU do you need for gemma poc finetune?
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: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.1 GB file, about 5.8 GB in use).
- 12 GB VRAM: the best quant that fits is BF16 (7.8 GB file, about 9.4 GB in use).
Which gemma poc finetune quant should you choose?
BF16 (7.8 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.
If memory is tight, the smallest file is Q8_0 at 4.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gemma poc finetune
How much VRAM does gemma poc finetune need?
About 9.4 GB at BF16 with an 8K context window. That is the 7.8 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 gemma poc finetune on an 8 GB GPU?
Yes, with Q8_0: the 4.1 GB file needs about 5.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma poc finetune GGUF?
It depends on the quant: Q8_0 is 4.1 GB, BF16 is 7.8 GB, F16 is 7.8 GB.
What context length does gemma poc finetune support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.6 GB at 32K.
Where can I download gemma poc finetune GGUF?
The files are on Hugging Face in the kygbjs/gemma-poc-finetune-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does gemma poc finetune use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.