MamayLM Gemma 3 12B IT v2.0 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 4 quants, from 7.3 GB (Q4_K_M) to 12.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
MamayLM Gemma 3 12B IT v2.0 – Ukrainian‑adapted vision‑language model
MamayLM Gemma 3 12B IT v2.0 is a 11.8B parameter model based on Gemma 3. It supports text and image inputs within a 131072‑token context. The model is fine‑tuned for Ukrainian alignment and instruction following.
Good at
- Vision‑language understanding
- Instruction following
- Long context handling
Limits
- No vision support in some tools
- Requires 8k context for memory estimates
- License is Gemma Terms of Use
Best for
- Multimodal chat in Ukrainian
- Long‑form content generation
- Instruction‑driven tasks
Who it’s for. Developers building Ukrainian‑centric multimodal applications or researchers needing a 12B vision‑language model with a large context window.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 7.3 GB | 11.0 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 Q4_K_M (7.3 GB file, ~11 GB memory at 8k context). For 12‑GB VRAM, Q5_K_M (8.45 GB file, ~12.2 GB memory). For 16‑GB VRAM, Q6_K (9.66 GB file, ~13.4 GB memory).
What GPU do you need for MamayLM Gemma 3 12B IT v2.0?
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 (7.3 GB file, about 11.0 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 MamayLM Gemma 3 12B IT v2.0 quant should you choose?
Q4_K_M is the usual starting point for MamayLM Gemma 3 12B IT v2.0: 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.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about MamayLM Gemma 3 12B IT v2.0
How much VRAM does MamayLM Gemma 3 12B IT v2.0 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 MamayLM Gemma 3 12B IT v2.0 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.
What is the file size of MamayLM Gemma 3 12B IT v2.0 GGUF?
It depends on the quant: Q4_K_M is 7.3 GB, Q5_K_M is 8.4 GB, Q6_K is 9.7 GB, Q8_0 is 12.5 GB.
What context length does MamayLM Gemma 3 12B IT v2.0 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 MamayLM Gemma 3 12B IT v2.0 GGUF?
The files are on Hugging Face in the INSAIT-Institute/MamayLM-Gemma-3-12B-IT-v2.0-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 MamayLM Gemma 3 12B IT v2.0 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 MamayLM Gemma 3 12B IT v2.0 on 8 GB VRAM?
Yes, the Q4_K_M quantization uses 7.3 GB file size and requires about 11 GB memory at 8k context, which fits an 8 GB VRAM setup with some swapping.
Does the model support image inputs?
Yes, it has vision‑language understanding and can process images within the same context as text.
What context length does it support?
The model is trained with a 131072‑token context window, enabling very long conversations and documents.