PO

POLAR-14B-DPO-v1.3

PolarGGUF by mradermacherUpdated 2024-05-24
Download on Hugging Face
Parameters14.2B
Context4K
Layers64
Architecturellama
Smallest quant5.3 GB
Quick answer

POLAR-14B-DPO-v1.3 needs about 11.2 GB of memory at Q4_K_M (a 8.6 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 5.3 GB (Q2_K) to 15.1 GB (Q8_0).

POLAR-14B-DPO-v1.3: 14.2B Korean LLM in GGUF format

POLAR-14B-DPO-v1.3 is a 14.2B parameter Korean language model. It is trained with DPO data and released under the apache-2.0 license. The model supports a 4096 token context window.

Good at

  • Korean language generation
  • DPO‑trained responses
  • LLM inference in GGUF format

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No explicit language list beyond Korean

Best for

  • Chatbots in Korean
  • Content creation in Korean
  • Research on Korean LLMs

Who it’s for. Developers and researchers needing a Korean language model for inference or fine‑tuning. The model is suitable for applications that can run GGUF files and have sufficient GPU memory.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K5.3 GB 6.9 GB
Fits Get file →
IQ3_XS5.9 GB 7.4 GB
Tight Get file →
Q3_K_S6.2 GB 7.7 GB
Tight Get file →
IQ3_S6.2 GB 7.8 GB
Tight Get file →
IQ3_M6.4 GB 8.0 GB
Tight Get file →
Q3_K_M6.9 GB 8.4 GB
Too big Get file →
Q3_K_L7.5 GB 9.1 GB
Too big Get file →
IQ4_XS7.7 GB 9.3 GB
Too big Get file →
Q4_K_S8.1 GB 9.7 GB
Too big Get file →
Q4_K_M8.6 GB 10.1 GB
Too big Get file →
Q5_K_S9.8 GB 11.4 GB
Too big Get file →
Q5_K_M10.1 GB 11.6 GB
Too big Get file →
Q6_K11.7 GB 13.2 GB
Too big Get file →
Q8_015.1 GB 16.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K (file size 5.29 GB, estimated 7.9 GB memory). For 12 GB VRAM, Q4_K_M (8.55 GB, 11.2 GB memory) is a good balance. For 16 GB VRAM, Q5_K_M (10.06 GB, 12.7 GB memory) provides higher quality.

What GPU do you need for POLAR-14B-DPO-v1.3?

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: the best quant that fits is Q2_K (5.3 GB file, about 7.9 GB in use).
  • 12 GB VRAM: the best quant that fits is Q4_K_M (8.6 GB file, about 11.2 GB in use).
  • 16 GB VRAM: the best quant that fits is Q6_K (11.7 GB file, about 14.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (15.1 GB file, about 17.8 GB in use).

Which POLAR-14B-DPO-v1.3 quant should you choose?

Q4_K_M is the usual starting point for POLAR-14B-DPO-v1.3: it balances file size and quality well. Here it is a 8.6 GB file.

The Q8_0 file is 15.1 GB, about 1.8 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.

If memory is tight, the smallest file is Q2_K at 5.3 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
Parameters14.2B
Layers64
Trained context4,096 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyPolar
Licenseapache-2.0
Downloads (HF)567
Last updated2024-05-24

Frequently asked questions about POLAR-14B-DPO-v1.3

How much VRAM does POLAR-14B-DPO-v1.3 need?

About 11.2 GB at Q4_K_M with an 8K context window. That is the 8.6 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 POLAR-14B-DPO-v1.3 on an 8 GB GPU?

Yes, with Q2_K: the 5.3 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 POLAR-14B-DPO-v1.3 GGUF?

It depends on the quant: Q2_K is 5.3 GB, IQ3_XS is 5.9 GB, Q3_K_S is 6.2 GB, IQ3_S is 6.2 GB, IQ3_M is 6.4 GB, Q3_K_M is 6.9 GB and 8 more.

What context length does POLAR-14B-DPO-v1.3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.1 GB at 8K and 1.1 GB at 4K.

Where can I download POLAR-14B-DPO-v1.3 GGUF?

The files are on Hugging Face in the mradermacher/POLAR-14B-DPO-v1.3-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 POLAR-14B-DPO-v1.3 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 POLAR-14B-DPO-v1.3 on 8 GB VRAM?

Yes, the Q2_K quant uses 5.29 GB file size and estimates 7.9 GB memory at 8k context.

Does POLAR-14B-DPO-v1.3 support vision tasks?

No, the model is a language model only and does not support vision.

Other GGUFs of POLAR-14B-DPO-v1.3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Polar models

All Polar →

Other medium models

All medium models →