ReWiz Gemma2 9B needs about 9.1 GB of memory at Q4_K_M (a 5.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 8 quants, from 4.3 GB (Q3_K_S) to 18.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 11.3 GB.
ReWiz Gemma2 9B is a 9.24B-parameter Gemma model in GGUF format, quantized by theprint. Its trained context length is 32K tokens. The repository has 8 quant files, from 4.3 GB (Q3_K_S) to 18.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 4.3 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_M | 4.8 GB | 8.1 GB | Too big | Get file → | |
| Q4_K_S | 5.5 GB | 8.8 GB | Too big | Get file → | |
| Q4_K_M | 5.8 GB | 9.1 GB | Too big | Get file → | |
| Q5_K_M | 6.6 GB | 10.0 GB | Too big | Get file → | |
| Q6_K | 7.6 GB | 10.9 GB | Too big | Get file → | |
| Q8_0 | 9.8 GB | 13.1 GB | Too big | Get file → | |
| F16 | 18.5 GB | 21.8 GB | Too big | Get file → |
What GPU do you need for ReWiz Gemma2 9B?
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: the best quant that fits is Q3_K_S (4.3 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.6 GB file, about 10.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 13.1 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (18.5 GB file, about 21.8 GB in use).
Which ReWiz Gemma2 9B quant should you choose?
Q4_K_M is the usual starting point for ReWiz Gemma2 9B: it balances file size and quality well. Here it is a 5.8 GB file.
The Q8_0 file is 9.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_S at 4.3 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about ReWiz Gemma2 9B
How much VRAM does ReWiz Gemma2 9B need?
About 9.1 GB at Q4_K_M with an 8K context window. That is the 5.8 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 ReWiz Gemma2 9B on an 8 GB GPU?
Yes, with Q3_K_S: the 4.3 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ReWiz Gemma2 9B GGUF?
It depends on the quant: Q3_K_S is 4.3 GB, Q3_K_M is 4.8 GB, Q4_K_S is 5.5 GB, Q4_K_M is 5.8 GB, Q5_K_M is 6.6 GB, Q6_K is 7.6 GB and 2 more.
What context length does ReWiz Gemma2 9B support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 2.8 GB at 8K and 11.3 GB at 32K.
Where can I download ReWiz Gemma2 9B GGUF?
The files are on Hugging Face in the theprint/ReWiz-Gemma2-9B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does ReWiz Gemma2 9B 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.