KO

kona2 12B i1

KonaGGUF by mradermacherUpdated 2026-06-09
Download on Hugging Face
Parameters12.5B
Context1000K
Layers40
Architecturellama
Smallest quant0.0 GB
Quick answer

kona2 12B i1 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 i1: 12.5B‑parameter Georgian/English LLM

Kona2‑12B i1 is a 12.5‑billion parameter model built on the Kona family. It supports Georgian and English, trained with Direct Preference Optimization for higher quality and alignment. The model is released under Apache‑2.0.

Good at

  • High‑quality question answering
  • Function/tool calling
  • Translation

Limits

  • No vision support
  • Requires 24GB VRAM for 4‑bit quant
  • Training data cutoff 2024

Best for

  • Production conversational AI
  • Customer support automation
  • Content generation

Who it’s for. Developers and enterprises needing a multilingual LLM for Georgian and English. The model is suitable for production use with sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.8 GB
Fits Get file →
IQ1_S3.1 GB 4.9 GB
Fits Get file →
IQ1_M3.3 GB 5.2 GB
Fits Get file →
IQ2_XXS3.7 GB 5.5 GB
Fits Get file →
IQ2_XS4.0 GB 5.9 GB
Fits Get file →
IQ2_S4.3 GB 6.1 GB
Fits Get file →
IQ2_M4.6 GB 6.4 GB
Fits Get file →
Q2_K_S4.6 GB 6.5 GB
Fits Get file →
Q2_K4.9 GB 6.8 GB
Fits Get file →
IQ3_XXS5.1 GB 6.9 GB
Fits Get file →
IQ3_XS5.4 GB 7.3 GB
Tight Get file →
Q3_K_S5.7 GB 7.5 GB
Tight Get file →
IQ3_S5.7 GB 7.5 GB
Tight Get file →
IQ3_M5.9 GB 7.7 GB
Tight Get file →
Q3_K_M6.2 GB 8.1 GB
Too big Get file →
Q3_K_L6.7 GB 8.5 GB
Too big Get file →
IQ4_XS6.9 GB 8.7 GB
Too big Get file →
Q4_07.2 GB 9.1 GB
Too big Get file →
IQ4_NL7.2 GB 9.1 GB
Too big Get file →
Q4_K_S7.3 GB 9.1 GB
Too big Get file →
Q4_K_M7.6 GB 9.5 GB
Too big Get file →
Q4_17.9 GB 9.8 GB
Too big Get file →
Q5_K_S8.7 GB 10.5 GB
Too big Get file →
Q5_K_M8.9 GB 10.7 GB
Too big Get file →
Q6_K10.2 GB 12.1 GB
Too big Get file →

For 8GB VRAM use IQ1_S (3.1 GB, 4.9 GB memory at 8k). For 16GB VRAM use IQ2_XS (4.02 GB, 5.9 GB memory). For 24GB VRAM use Q4_K_M (7.62 GB, 9.5 GB memory).

What GPU do you need for kona2 12B i1?

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 i1 quant should you choose?

Q4_K_M is the usual starting point for kona2 12B i1: 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

Architecturellama
Parameters12.5B
Layers40
Trained context1,024,000 tokens
KV cache (fp16)160 KB per token

Source

Quantized bymradermacher
FamilyKona
Licenseapache-2.0
Downloads (HF)801
Last updated2026-06-09

Frequently asked questions about kona2 12B i1

How much VRAM does kona2 12B i1 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 i1 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 i1 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 i1 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 i1 GGUF?

The files are on Hugging Face in the mradermacher/kona2-12B-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 i1 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 i1 on 8GB VRAM?

Use the IQ1_S quant, which is 3.1 GB and requires about 4.9 GB of VRAM at 8k context.

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.

Other GGUFs of kona2-12B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Kona models

All Kona →

Other medium models

All medium models →