Kenanga 12B IT DPO needs about 11.6 GB of memory at Q4_K_M (a 7.9 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 10.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 12.9 GB.
Kenanga 12B IT DPO – a 12.8B Gemma3 model in GGUF format
Kenanga 12B IT DPO is a 12.8B parameter Gemma3 model quantized for use with llama.cpp. It supports a 131072 token context window and is available in multiple quantization levels. The model is provided in GGUF format with various file sizes and memory estimates.
Good at
- Large context handling
- Flexible quantization options
- High token capacity
Limits
- No vision support in the provided files
- License not specified
- No mixture of experts
Best for
- Chat applications needing long context
- Fine‑tuning on local hardware
- Research on Gemma3 architecture
Who it’s for. Developers and researchers who need a large‑context Gemma3 model that can be run locally with llama.cpp. The model is suitable for those who can manage the memory requirements of the chosen quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.7 GB | Fits | Get file → | |
| IQ1_S | 3.3 GB | 7.0 GB | Fits | Get file → | |
| IQ1_M | 3.5 GB | 7.2 GB | Tight | Get file → | |
| IQ2_XXS | 3.9 GB | 7.6 GB | Tight | Get file → | |
| IQ2_XS | 4.2 GB | 7.9 GB | Tight | Get file → | |
| IQ2_S | 4.5 GB | 8.2 GB | Too big | Get file → | |
| IQ2_M | 4.7 GB | 8.5 GB | Too big | Get file → | |
| Q2_K_S | 4.8 GB | 8.5 GB | Too big | Get file → | |
| Q2_K | 5.1 GB | 8.8 GB | Too big | Get file → | |
| IQ3_XXS | 5.2 GB | 8.9 GB | Too big | Get file → | |
| IQ3_XS | 5.6 GB | 9.4 GB | Too big | Get file → | |
| IQ3_S | 5.9 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_S | 5.9 GB | 9.6 GB | Too big | Get file → | |
| IQ3_M | 6.1 GB | 9.8 GB | Too big | Get file → | |
| Q3_K_M | 6.4 GB | 10.2 GB | Too big | Get file → | |
| Q3_K_L | 6.9 GB | 10.6 GB | Too big | Get file → | |
| IQ4_XS | 7.1 GB | 10.8 GB | Too big | Get file → | |
| IQ4_NL | 7.5 GB | 11.2 GB | Too big | Get file → | |
| Q4_0 | 7.5 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_S | 7.5 GB | 11.2 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 11.6 GB | Too big | Get file → | |
| Q4_1 | 8.2 GB | 11.9 GB | Too big | Get file → | |
| Q5_K_S | 8.9 GB | 12.6 GB | Too big | Get file → | |
| Q5_K_M | 9.1 GB | 12.9 GB | Too big | Get file → | |
| Q6_K | 10.5 GB | 14.2 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (3.28 GB, 7 GB memory) or IQ1_M (3.5 GB, 7.2 GB memory). For 12 GB VRAM, IQ2_S (4.45 GB, 8.2 GB memory) or Q2_K (5.1 GB, 8.8 GB memory) are good choices. For 16 GB VRAM, Q3_K_M (6.44 GB, 10.2 GB memory) or Q4_K_M (7.87 GB, 11.6 GB memory) provide higher quality.
What GPU do you need for Kenanga 12B IT DPO?
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 3.7 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.7 GB in use).
- 8 GB VRAM: the best quant that fits is IQ2_XS (4.2 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_1 (8.2 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.5 GB file, about 14.2 GB in use).
Which Kenanga 12B IT DPO quant should you choose?
Q4_K_M is the usual starting point for Kenanga 12B IT DPO: it balances file size and quality well. Here it is a 7.9 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 Kenanga 12B IT DPO
How much VRAM does Kenanga 12B IT DPO need?
About 11.6 GB at Q4_K_M with an 8K context window. That is the 7.9 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 Kenanga 12B IT DPO on an 8 GB GPU?
Yes, with IQ2_XS: the 4.2 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Kenanga 12B IT DPO GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 3.3 GB, IQ1_M is 3.5 GB, IQ2_XXS is 3.9 GB, IQ2_XS is 4.2 GB, IQ2_S is 4.5 GB and 19 more.
What context length does Kenanga 12B IT DPO 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 Kenanga 12B IT DPO GGUF?
The files are on Hugging Face in the mradermacher/Kenanga-12B-IT-DPO-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Kenanga 12B IT DPO on 8 GB VRAM?
Yes, with IQ1_S or IQ1_M quantization, which use about 7 GB of VRAM at 8k context.
Does this model support vision tasks?
No, the provided GGUF files are text-only. Vision support would require separate mmproj files.
What is the maximum context length?
The model supports up to 131072 tokens in context.