grabbe ai 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 3 quants, from 5.8 GB (Q4_K_M) to 18.5 GB (F16).
GrabbeAI – a 9.24B Gemma2 model for school digital assistance
GrabbeAI is a 9.24‑billion‑parameter Gemma2 model developed by the Christian‑Dietrich‑Grabbe‑Gymnasium. It is trained on 8192 context tokens and released under the gemma license. The model is available in three GGUF quantizations.
Good at
- School‑specific digital assistance
- Student‑teacher‑parent communication
- Web‑app integration
Limits
- No vision support
- License restricts commercial use
- Context limited to 8192 tokens
Best for
- Automating school FAQs
- Assisting teachers with lesson planning
- Supporting parent‑school communication
Who it’s for. Educators, school administrators, and developers building school‑focused AI assistants. The model is tailored for educational environments and can be deployed on the school’s website or a dedicated web‑app.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 5.8 GB | 9.1 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 → |
For 8 GB VRAM use the Q4_K_M quant (5.76 GB file, ~9.1 GB memory at 8k context). With 12 GB VRAM the Q8_0 quant (9.83 GB file, ~13.1 GB memory) is suitable. For larger GPUs, the F16 quant (18.49 GB file, ~21.8 GB memory) offers full precision.
What GPU do you need for grabbe ai?
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 Q4_K_M (5.8 GB file, about 9.1 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 grabbe ai quant should you choose?
Q4_K_M is the usual starting point for grabbe ai: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about grabbe ai
How much VRAM does grabbe ai 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 grabbe ai on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of grabbe ai GGUF?
It depends on the quant: Q4_K_M is 5.8 GB, Q8_0 is 9.8 GB, F16 is 18.5 GB.
What context length does grabbe ai support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 2.8 GB at 8K and 2.8 GB at 8K.
Where can I download grabbe ai GGUF?
The files are on Hugging Face in the grabbe-gymnasium-detmold/grabbe-ai repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does grabbe ai 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 GrabbeAI on 8 GB VRAM?
Yes, the Q4_K_M quant requires 5.76 GB file size and estimates 9.1 GB memory at 8k context, fitting within 8 GB VRAM with some overhead.
Does GrabbeAI support image input?
No, the model has no vision capabilities and is text‑only.