LL

Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base

LlamaGGUF by mradermacherUpdated 2024-12-16
Download on Hugging Face
Parameters8B
Context8K
Layers32
Architecturellama
Smallest quant2.0 GB
Quick answer

Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base needs about 6.5 GB of memory at Q4_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 21 quants, from 2.0 GB (IQ1_S) to 6.6 GB (Q6_K).

Linkbricks Korean Llama3 8B Instruct DPO model

Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base is an 8B Llama3 model trained on Korean data with instruction fine‑tuning and DPO. It supports 8192 token context and is released under apache-2.0. The tokenizer matches Llama3 and includes Korean vocabulary.

Good at

  • Instruction following
  • Korean language support
  • Fine‑tuned dialogue

Limits

  • No vision capability
  • Requires 8192 token context
  • License is apache-2.0

Best for

  • Chatbot development
  • Korean content generation
  • Instruction‑based applications

Who it’s for. Developers building Korean language chatbots or content generators who need a fine‑tuned Llama3 model. The model is suitable for projects that can run on GPU hardware with at least 8 GB VRAM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.0 GB 3.6 GB
Fits Get file →
IQ1_M2.2 GB 3.7 GB
Fits Get file →
IQ2_XXS2.4 GB 4.0 GB
Fits Get file →
IQ2_XS2.6 GB 4.2 GB
Fits Get file →
IQ2_S2.8 GB 4.3 GB
Fits Get file →
IQ2_M2.9 GB 4.5 GB
Fits Get file →
Q2_K3.2 GB 4.8 GB
Fits Get file →
IQ3_XXS3.3 GB 4.8 GB
Fits Get file →
IQ3_XS3.5 GB 5.1 GB
Fits Get file →
Q3_K_S3.7 GB 5.2 GB
Fits Get file →
IQ3_S3.7 GB 5.3 GB
Fits Get file →
IQ3_M3.8 GB 5.4 GB
Fits Get file →
Q3_K_M4.0 GB 5.6 GB
Fits Get file →
Q3_K_L4.3 GB 5.9 GB
Fits Get file →
IQ4_XS4.4 GB 6.0 GB
Fits Get file →
Q4_04.7 GB 6.2 GB
Fits Get file →
Q4_K_S4.7 GB 6.3 GB
Fits Get file →
Q4_K_M4.9 GB 6.5 GB
Fits Get file →
Q5_K_S5.6 GB 7.2 GB
Fits Get file →
Q5_K_M5.7 GB 7.3 GB
Tight Get file →
Q6_K6.6 GB 8.2 GB
Too big Get file →

For 8 GB VRAM use IQ1_S (2.02 GB, 3.6 GB memory) or IQ1_M (2.16 GB, 3.7 GB). With 12 GB VRAM IQ2_S (2.76 GB, 4.3 GB) or Q2_K (3.18 GB, 4.8 GB) are suitable. For 16 GB VRAM use Q3_K_L (4.32 GB, 5.9 GB) or Q4_K_M (4.92 GB, 6.5 GB).

What GPU do you need for Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base?

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 IQ2_XXS (2.4 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is IQ4_XS (4.4 GB file, about 6.0 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.7 GB file, about 7.3 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.6 GB file, about 8.2 GB in use).

Which Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base quant should you choose?

Q4_K_M is the usual starting point for Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base: it balances file size and quality well. Here it is a 4.9 GB file.

If memory is tight, the smallest file is IQ1_S at 2.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters8B
Layers32
Trained context8,192 tokens
KV cache (fp16)128 KB per token

Frequently asked questions about Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base

How much VRAM does Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base need?

About 6.5 GB at Q4_K_M with an 8K context window. That is the 4.9 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 Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base on an 8 GB GPU?

Yes, with Q5_K_M: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base GGUF?

It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.6 GB, IQ2_S is 2.8 GB, IQ2_M is 2.9 GB and 15 more.

What context length does Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base support?

The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.

Where can I download Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base GGUF?

The files are on Hugging Face in the mradermacher/Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base-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 Linkbricks-Horizon-AI-Ko-llama3-Instruct-dpo-8B-base 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, use IQ1_S or IQ1_M quantizations; they require about 3.6–3.7 GB VRAM at 8k context.

Does this model support Korean text?

Yes, the tokenizer includes Korean vocabulary and the model was trained on Korean data.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of Linkbricks-Horizon-AI-Korean-llama3-sft-dpo-8b-base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Llama models

All Llama →

Other small models

All small models →