gemma needs about 8.4 GB of memory at Q5_K_S (a 7.0 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 2.2 GB to 9.8 GB (Q8_0).
gemma is a 10B-parameter Gemma model in GGUF format, quantized by pneumix. Its trained context length is 8K tokens. The repository has 5 quant files, from 2.2 GB to 9.8 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 2.2 GB | 3.5 GB | Fits | Get file → | |
| Q5_K_M | 6.6 GB | 8.0 GB | Too big | Get file → | |
| Q5_K_S | 7.0 GB | 8.4 GB | Too big | Get file → | |
| Q6_K | 7.6 GB | 9.0 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 11.2 GB | Too big | Get file → |
What GPU do you need for gemma?
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: the best quant that fits is the main file (2.2 GB file, about 3.5 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (2.2 GB file, about 3.5 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K_M (6.6 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.2 GB in use).
Which gemma quant should you choose?
Q5_K_S (7.0 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is the first one in the table at 2.2 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about gemma
How much VRAM does gemma need?
About 8.4 GB at Q5_K_S with an 8K context window. That is the 7.0 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 on an 8 GB GPU?
Yes, with Q5_K_M: the 6.6 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma GGUF?
It depends on the quant: file is 2.2 GB, Q5_K_M is 6.6 GB, Q5_K_S is 7.0 GB, Q6_K is 7.6 GB, Q8_0 is 9.8 GB.
What context length does gemma support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.9 GB at 8K and 0.9 GB at 8K.
Where can I download gemma GGUF?
The files are on Hugging Face in the pneumix/gemma repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.