GaMS3 12B Multimodal needs about 11.0 GB of memory at Q4_K_M (a 7.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 11 quants, from 4.8 GB (Q2_K) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
GaMS3 12B Multimodal – Vision Language Model in Slovene
GaMS3 12B Multimodal is a 11.8 billion‑parameter vision language model based on gemma3. It supports vision question answering and is fine‑tuned on a curated Slovene text‑image dataset. The model is released under the MIT license.
Good at
- Vision question answering
- Multimodal instruction following
- Slovene language support
Limits
- No vision support beyond image input
- Large VRAM requirement for higher quants
- No external vision APIs
Best for
- Image captioning in Slovene
- Visual QA for local applications
- Multimodal chatbots
Who it’s for. Developers building Slovene‑centric vision‑language applications. Researchers needing a multimodal model with a modest parameter count and open‑source license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 4.8 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_S | 5.5 GB | 9.2 GB | Too big | Get file → | |
| Q3_K_M | 6.0 GB | 9.7 GB | Too big | Get file → | |
| Q3_K_L | 6.5 GB | 10.2 GB | Too big | Get file → | |
| IQ4_XS | 6.6 GB | 10.3 GB | Too big | Get file → | |
| Q4_K_S | 6.9 GB | 10.7 GB | Too big | Get file → | |
| Q4_K_M | 7.3 GB | 11.0 GB | Too big | Get file → | |
| Q5_K_S | 8.2 GB | 12.0 GB | Too big | Get file → | |
| Q5_K_M | 8.4 GB | 12.2 GB | Too big | Get file → | |
| Q6_K | 9.7 GB | 13.4 GB | Too big | Get file → | |
| Q8_0 | 12.5 GB | 16.2 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (4.77 GB, 8.5 GB RAM) or Q3_K_S (5.46 GB, 9.2 GB RAM). With 12 GB VRAM, Q4_K_M (7.3 GB, 11 GB RAM) or Q5_K_M (8.45 GB, 12.2 GB RAM) are suitable. Larger quants require more VRAM.
What GPU do you need for GaMS3 12B Multimodal?
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 Q5_K_S (8.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (9.7 GB file, about 13.4 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (12.5 GB file, about 16.2 GB in use).
Which GaMS3 12B Multimodal quant should you choose?
Q4_K_M is the usual starting point for GaMS3 12B Multimodal: it balances file size and quality well. Here it is a 7.3 GB file.
The Q8_0 file is 12.5 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 Q2_K at 4.8 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 GaMS3 12B Multimodal
How much VRAM does GaMS3 12B Multimodal need?
About 11.0 GB at Q4_K_M with an 8K context window. That is the 7.3 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 GaMS3 12B Multimodal on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.5 GB, so you would need a larger GPU or CPU offloading.
What is the file size of GaMS3 12B Multimodal GGUF?
It depends on the quant: Q2_K is 4.8 GB, Q3_K_S is 5.5 GB, Q3_K_M is 6.0 GB, Q3_K_L is 6.5 GB, IQ4_XS is 6.6 GB, Q4_K_S is 6.9 GB and 5 more.
What context length does GaMS3 12B Multimodal support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 3.2 GB at 8K and 12.9 GB at 32K.
Where can I download GaMS3 12B Multimodal GGUF?
The files are on Hugging Face in the mradermacher/GaMS3-12B-Multimodal-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 GaMS3 12B Multimodal use?
Hugging Face lists the license as mit. 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 GaMS3 12B Multimodal on 8 GB VRAM?
Yes, using the Q2_K or Q3_K_S quantized files which fit within 8 GB VRAM and require about 8.5–9.2 GB RAM.
Does the model support other languages besides Slovene?
The model is fine‑tuned on Slovene data; other languages are not guaranteed to perform well.
What license applies to this model?
The model is released under the MIT license, allowing free use and modification.