Shieldgemma 27b needs about 16.0 GB of memory at IQ3_M (a 12.5 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 6.1 GB (IQ1_S) to 54.5 GB.
Shieldgemma 27b – 27.2B Gemini‑style model in GGUF format
Shieldgemma 27b is a 27.2B parameter model based on gemma2 architecture. It is quantized for llama.cpp and supports a 8192 token context. The model is released under the gemma license.
Good at
- Large context reasoning
- High‑capacity language modeling
- Fine‑tuned for 8k token usage
Limits
- No vision support
- Requires at least 9.7 GB VRAM for IQ1_S at 8k context
- License restricts commercial use
Best for
- Chatbots needing long context
- Research prototypes with 8k token limits
- Educational demos on modest GPUs
Who it’s for. Developers and researchers who need a large‑scale language model that can run on llama.cpp. The model is suitable for those with GPU memory between 10 GB and 30 GB and who are comfortable handling GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 6.1 GB | 9.7 GB | Too big | Get file → | |
| IQ1_M | 6.7 GB | 10.3 GB | Too big | Get file → | |
| IQ2_XXS | 7.6 GB | 11.2 GB | Too big | Get file → | |
| IQ2_XS | 8.4 GB | 12.0 GB | Too big | Get file → | |
| IQ2_S | 8.7 GB | 12.2 GB | Too big | Get file → | |
| IQ2_M | 9.4 GB | 13.0 GB | Too big | Get file → | |
| Q2_K_S | 9.7 GB | 13.3 GB | Too big | Get file → | |
| Q2_K | 10.4 GB | 14.0 GB | Too big | Get file → | |
| IQ3_XXS | 10.8 GB | 14.3 GB | Too big | Get file → | |
| IQ3_XS | 11.6 GB | 15.1 GB | Too big | Get file → | |
| IQ3_S | 12.2 GB | 15.8 GB | Too big | Get file → | |
| Q3_K_S | 12.2 GB | 15.8 GB | Too big | Get file → | |
| IQ3_M | 12.5 GB | 16.0 GB | Too big | Get file → | |
| Q3_K | 13.4 GB | 17.0 GB | Too big | Get file → | |
| Q3_K_L | 14.5 GB | 18.1 GB | Too big | Get file → | |
| IQ4_XS | 14.8 GB | 18.4 GB | Too big | Get file → | |
| IQ4_NL | 15.6 GB | 19.2 GB | Too big | Get file → | |
| Q4_K_S | 15.7 GB | 19.3 GB | Too big | Get file → | |
| Q4_K | 16.6 GB | 20.2 GB | Too big | Get file → | |
| Q5_K_S | 18.9 GB | 22.5 GB | Too big | Get file → | |
| Q5_K | 19.4 GB | 23.0 GB | Too big | Get file → | |
| Q6_K | 22.3 GB | 25.9 GB | Too big | Get file → | |
| Q8_0 | 28.9 GB | 32.5 GB | Too big | Get file → | |
| BF16 | 54.5 GB (3 parts) | 58.0 GB | Too big | Get file → | |
| — | 54.5 GB (3 parts) | 58.0 GB | Too big | Get file → |
For 10 GB VRAM, use IQ1_M (6.69 GB file, 10.3 GB memory). For 20 GB VRAM, Q4_K (16.65 GB file, 20.2 GB memory) is a good balance. For 30 GB VRAM, Q5_K (19.41 GB file, 23 GB memory) or Q6_K (22.34 GB file, 25.9 GB memory) are suitable. Estimates are approximate.
What GPU do you need for Shieldgemma 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: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_XS (8.4 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_M (12.5 GB file, about 16.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K (19.4 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.9 GB file, about 32.5 GB in use).
Which Shieldgemma 27b quant should you choose?
IQ3_M (12.5 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ1_S at 6.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Shieldgemma 27b
How much VRAM does Shieldgemma 27b need?
About 16.0 GB at IQ3_M with an 8K context window. That is the 12.5 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 Shieldgemma 27b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Shieldgemma 27b GGUF?
It depends on the quant: IQ1_S is 6.1 GB, IQ1_M is 6.7 GB, IQ2_XXS is 7.6 GB, IQ2_XS is 8.4 GB, IQ2_S is 8.7 GB, IQ2_M is 9.4 GB and 19 more.
What context length does Shieldgemma 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 Shieldgemma 27b GGUF?
The files are on Hugging Face in the legraphista/shieldgemma-27b-IMat-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 Shieldgemma 27b use?
Hugging Face lists the license as gemma. 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 Shieldgemma 27b on 8 GB VRAM?
The smallest quant IQ1_S requires 9.7 GB VRAM at 8k context, so 8 GB is insufficient.
Does Shieldgemma 27b support vision tasks?
No, the model has no vision capabilities.
How do I merge split GGUF files?
Use the gguf-split tool from the llama.cpp releases to merge split chunks.