Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B needs about 20.2 GB of memory at Q4_K_M (a 16.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 16.6 GB (Q4_K_M) to 28.9 GB (Q8_0).
Linkbricks Horizon AI Korean Gemma 2 27B fine‑tuned for Korean, Chinese, English, Japanese
Linkbricks Horizon AI released a Korean‑specialized Gemma‑2‑27B‑IT model. It was fine‑tuned with SFT→DPO on eight NVIDIA H100 80GB GPUs. The model supports cross‑lingual reasoning and high‑risk content detection.
Good at
- Cross‑lingual Korean/Chinese/English/Japanese reasoning
- High‑risk content detection
- Logical problem solving
Limits
- No vision support
- License: apache‑2.0
- Context length: 8192 tokens
Best for
- Korean language chatbots
- Cross‑lingual content moderation
- Logical reasoning tasks
Who it’s for. Developers building Korean‑centric applications that require robust cross‑lingual understanding and content safety. Suitable for enterprises needing high‑risk content detection in Korean, Chinese, English, and Japanese.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 16.6 GB | 20.2 GB | Too big | Get file → | |
| Q5_K_M | 19.4 GB | 23.0 GB | Too big | Get file → | |
| Q6_K | 22.3 GB | 25.9 GB | Too big | Get file → | |
| Q8_0 | 28.9 GB | 32.5 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K_M (file size 16.65 GB, estimated 20.2 GB memory). For 12 GB VRAM use Q5_K_M (19.41 GB, 23 GB). For 16 GB VRAM use Q6_K (22.34 GB, 25.9 GB). For 24 GB VRAM use Q8_0 (28.94 GB, 32.5 GB). Estimates are approximate.
What GPU do you need for Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.4 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.3 GB file, about 25.9 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.9 GB file, about 32.5 GB in use).
Which Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B quant should you choose?
Q4_K_M is the usual starting point for Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B: it balances file size and quality well. Here it is a 16.6 GB file.
The Q8_0 file is 28.9 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
Source
Frequently asked questions about Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B
How much VRAM does Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B need?
About 20.2 GB at Q4_K_M with an 8K context window. That is the 16.6 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 Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 20.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B GGUF?
It depends on the quant: Q4_K_M is 16.6 GB, Q5_K_M is 19.4 GB, Q6_K is 22.3 GB, Q8_0 is 28.9 GB.
What context length does Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 3.1 GB at 8K and 3.1 GB at 8K.
Where can I download Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B GGUF?
The files are on Hugging Face in the Saxo/Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Linkbricks-Horizon-AI-Korean-Gemma-2-sft-dpo-27B 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 this model on 8 GB VRAM?
Yes, using the Q4_K_M quantized file which requires about 20.2 GB of VRAM at 8k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What languages can it handle?
It is trained on Korean, Chinese, English, and Japanese and can perform cross‑lingual tasks across these languages.