gemma RCA needs about 2.2 GB of memory at Q4_0 (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 10 quants, from 1.3 GB (Q3_K_S) to 10.0 GB.
gemma RCA is a 2.51B-parameter Gemma model in GGUF format, quantized by siddharth797. Its trained context length is 8K tokens. The repository has 10 quant files, from 1.3 GB (Q3_K_S) to 10.0 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_S | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q3_K | 1.4 GB | 2.0 GB | Fits | Get file → | |
| Q3_K_M | 1.4 GB | 2.0 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.2 GB | Fits | Get file → | |
| IQ4_NL | 1.6 GB | 2.2 GB | Fits | Get file → | |
| Q4_1 | 1.7 GB | 2.3 GB | Fits | Get file → | |
| Q5_0 | 1.8 GB | 2.4 GB | Fits | Get file → | |
| Q5_1 | 1.9 GB | 2.6 GB | Fits | Get file → | |
| — | 10.0 GB | 10.7 GB | Too big | Get file → |
What GPU do you need for gemma RCA?
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 Q5_1 (1.9 GB file, about 2.6 GB in use).
- 6 GB VRAM: the best quant that fits is Q5_1 (1.9 GB file, about 2.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_1 (1.9 GB file, about 2.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (10.0 GB file, about 10.7 GB in use).
Which gemma RCA quant should you choose?
Q4_0 (1.6 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
If memory is tight, the smallest file is Q3_K_S at 1.3 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 gemma RCA
How much VRAM does gemma RCA need?
About 2.2 GB at Q4_0 with an 8K context window. That is the 1.6 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 RCA on an 8 GB GPU?
Yes, with Q5_1: the 1.9 GB file needs about 2.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of gemma RCA GGUF?
It depends on the quant: Q3_K_S is 1.3 GB, Q3_K is 1.4 GB, Q3_K_M is 1.4 GB, IQ4_XS is 1.5 GB, Q4_0 is 1.6 GB, IQ4_NL is 1.6 GB and 4 more.
What context length does gemma RCA support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.2 GB at 8K.
Where can I download gemma RCA GGUF?
The files are on Hugging Face in the siddharth797/gemma-RCA-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.