Kona2 12B Instruct needs about 9.5 GB of memory at Q4_K_M (a 7.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 10.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
Kona2 12B Instruct – 12‑billion parameter instruction‑tuned model for Georgian and English
Kona2 12B Instruct is a 12‑billion parameter instruction‑tuned language model. It is built on Kona2‑12B‑Base and trained with supervised fine‑tuning. The model supports chat, question answering, function calling and translation between Georgian and English.
Good at
- Chat and question answering
- Function and tool calling
- Georgian‑English translation
Limits
- No vision support
- Training data cutoff 2024
- Requires 24GB VRAM for 4‑bit quantization
Best for
- Conversational AI assistants
- Information retrieval
- Code generation and explanation
Who it’s for. Developers building multilingual assistants or translation tools that need Georgian and English support. Researchers needing a 12‑billion parameter model for instruction‑tuned tasks.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.8 GB | Fits | Get file → | |
| IQ1_S | 3.1 GB | 4.9 GB | Fits | Get file → | |
| IQ1_M | 3.3 GB | 5.2 GB | Fits | Get file → | |
| IQ2_XXS | 3.7 GB | 5.5 GB | Fits | Get file → | |
| IQ2_XS | 4.0 GB | 5.9 GB | Fits | Get file → | |
| IQ2_S | 4.3 GB | 6.1 GB | Fits | Get file → | |
| IQ2_M | 4.6 GB | 6.4 GB | Fits | Get file → | |
| Q2_K_S | 4.6 GB | 6.5 GB | Fits | Get file → | |
| Q2_K | 4.9 GB | 6.8 GB | Fits | Get file → | |
| IQ3_XXS | 5.1 GB | 6.9 GB | Fits | Get file → | |
| IQ3_XS | 5.4 GB | 7.3 GB | Tight | Get file → | |
| Q3_K_S | 5.7 GB | 7.5 GB | Tight | Get file → | |
| IQ3_S | 5.7 GB | 7.5 GB | Tight | Get file → | |
| IQ3_M | 5.9 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_M | 6.2 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_L | 6.7 GB | 8.5 GB | Too big | Get file → | |
| IQ4_XS | 6.9 GB | 8.7 GB | Too big | Get file → | |
| Q4_0 | 7.2 GB | 9.1 GB | Too big | Get file → | |
| IQ4_NL | 7.2 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_S | 7.3 GB | 9.1 GB | Too big | Get file → | |
| Q4_K_M | 7.6 GB | 9.5 GB | Too big | Get file → | |
| Q4_1 | 7.9 GB | 9.8 GB | Too big | Get file → | |
| Q5_K_S | 8.7 GB | 10.5 GB | Too big | Get file → | |
| Q5_K_M | 8.9 GB | 10.7 GB | Too big | Get file → | |
| Q6_K | 10.2 GB | 12.1 GB | Too big | Get file → |
For 8GB VRAM use Q4_K_M (file size 7.62 GB, memory 9.5 GB). For 16GB VRAM use Q3_K_M (file size 6.21 GB, memory 8.1 GB). For 24GB VRAM use IQ1_S (file size 3.1 GB, memory 4.9 GB). Memory estimates are approximate.
What GPU do you need for Kona2 12B Instruct?
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 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is IQ2_XS (4.0 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_M (5.9 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (8.9 GB file, about 10.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.2 GB file, about 12.1 GB in use).
Which Kona2 12B Instruct quant should you choose?
Q4_K_M is the usual starting point for Kona2 12B Instruct: it balances file size and quality well. Here it is a 7.6 GB file.
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 Kona2 12B Instruct
How much VRAM does Kona2 12B Instruct need?
About 9.5 GB at Q4_K_M with an 8K context window. That is the 7.6 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 Kona2 12B Instruct on an 8 GB GPU?
Yes, with IQ3_M: the 5.9 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kona2 12B Instruct GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.1 GB, IQ1_M is 3.3 GB, IQ2_XXS is 3.7 GB, IQ2_XS is 4.0 GB, IQ2_S is 4.3 GB and 19 more.
What context length does Kona2 12B Instruct support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download Kona2 12B Instruct GGUF?
The files are on Hugging Face in the mradermacher/kona2-12B-Instruct-i1-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 Kona2 12B Instruct use?
Hugging Face lists the license as apache-2.0. 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 Kona2 12B Instruct on 8GB VRAM?
Use the Q4_K_M quant; it requires about 9.5 GB VRAM at 8k context, so 8GB may be insufficient.
Does the model support vision tasks?
No, the model has no vision support.
What license does the model use?
The model is released under the Apache 2.0 License.