C2S-Scale-Gemma-2-27B needs about 20.3 GB of memory at Q4_K_M (a 16.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 27 quants, from 0.0 GB to 54.5 GB (BF16).
C2S-Scale-Gemma-2-27B: 27.2B parameter model fine‑tuned for single‑cell biology
C2S-Scale-Gemma-2-27B is a 27.2B parameter Gemma‑2 model. It is fine‑tuned to interpret single‑cell RNA sequencing data as language. The model supports a context length of 8192 tokens.
Good at
- Interpreting scRNA‑seq data
- Generating cell‑sentence representations
- Fine‑tuned for biology
Limits
- No vision support
- Requires 8192 token context
- CC‑BY‑4.0 license
Best for
- Single‑cell data analysis
- Cell‑sentence generation
- Biological text generation
Who it’s for. Researchers and developers working with single‑cell RNA sequencing who need a language‑model approach to data analysis. The model is open‑source under CC‑BY‑4.0 and can be run locally with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.6 GB | Fits | Get file → | |
| IQ1_S | 7.2 GB | 10.8 GB | Too big | Get file → | |
| IQ1_M | 8.0 GB | 11.6 GB | Too big | Get file → | |
| IQ2_XXS | 8.4 GB | 12.0 GB | Too big | Get file → | |
| IQ2_XS | 9.1 GB | 12.7 GB | Too big | Get file → | |
| IQ2_S | 9.4 GB | 13.0 GB | Too big | Get file → | |
| IQ2_M | 9.9 GB | 13.5 GB | Too big | Get file → | |
| Q2_K_S | 10.1 GB | 13.7 GB | Too big | Get file → | |
| Q2_K_M | 10.3 GB | 13.8 GB | Too big | Get file → | |
| IQ3_XXS | 11.5 GB | 15.1 GB | Too big | Get file → | |
| IQ3_XS | 11.7 GB | 15.3 GB | Too big | Get file → | |
| IQ3_M | 13.1 GB | 16.7 GB | Too big | Get file → | |
| Q3_K_S | 13.2 GB | 16.8 GB | Too big | Get file → | |
| Q3_K_M | 13.4 GB | 16.9 GB | Too big | Get file → | |
| IQ4_XS | 14.8 GB | 18.4 GB | Too big | Get file → | |
| IQ4_NL | 15.3 GB | 18.9 GB | Too big | Get file → | |
| Q4_K_S | 15.9 GB | 19.5 GB | Too big | Get file → | |
| Q4_0 | 15.9 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_M | 16.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_1 | 17.1 GB | 20.7 GB | Too big | Get file → | |
| Q5_0 | 19.2 GB | 22.8 GB | Too big | Get file → | |
| Q5_K_M | 19.7 GB | 23.3 GB | Too big | Get file → | |
| Q5_1 | 20.8 GB | 24.4 GB | Too big | Get file → | |
| Q6_K_M | 22.6 GB | 26.2 GB | Too big | Get file → | |
| Q8_0 | 28.9 GB | 32.5 GB | Too big | Get file → | |
| F16 | 38.6 GB | 42.2 GB | Too big | Get file → | |
| BF16 | 54.5 GB (2 parts) | 58.0 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (7.25 GB, 10.8 GB memory). For 12‑GB VRAM, IQ2_XS (9.13 GB, 12.7 GB memory). For 20‑GB VRAM, Q4_K_M (16.72 GB, 20.3 GB memory).
What GPU do you need for C2S-Scale-Gemma-2-27B?
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 (0.0 GB file, about 3.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.6 GB in use).
- 12 GB VRAM: the best quant that fits is IQ2_XXS (8.4 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_XS (11.7 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.7 GB file, about 23.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K_M (22.6 GB file, about 26.2 GB in use).
- 48 GB VRAM: the best quant that fits is F16 (38.6 GB file, about 42.2 GB in use).
Which C2S-Scale-Gemma-2-27B quant should you choose?
Q4_K_M is the usual starting point for C2S-Scale-Gemma-2-27B: it balances file size and quality well. Here it is a 16.7 GB file.
The Q8_0 file is 28.9 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 the first one in the table at 0.0 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
Source
Frequently asked questions about C2S-Scale-Gemma-2-27B
How much VRAM does C2S-Scale-Gemma-2-27B need?
About 20.3 GB at Q4_K_M with an 8K context window. That is the 16.7 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 C2S-Scale-Gemma-2-27B on an 8 GB GPU?
Yes, with the smaller files: the 0.0 GB file needs about 3.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of C2S-Scale-Gemma-2-27B GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 7.2 GB, IQ1_M is 8.0 GB, IQ2_XXS is 8.4 GB, IQ2_XS is 9.1 GB, IQ2_S is 9.4 GB and 21 more.
What context length does C2S-Scale-Gemma-2-27B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.
Where can I download C2S-Scale-Gemma-2-27B GGUF?
The files are on Hugging Face in the Mungert/C2S-Scale-Gemma-2-27B-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 C2S-Scale-Gemma-2-27B use?
Hugging Face lists the license as cc-by-4.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run C2S-Scale-Gemma-2-27B on 8 GB VRAM?
Yes, the IQ1_S quantization uses 7.25 GB file size and requires about 10.8 GB VRAM at 8k context.
Does the model support vision tasks?
No, the model is a text‑only language model and does not support vision.
What license does the model use?
The model is released under CC‑BY‑4.0.