CU

Custom KoLLM 13B v3 i1

CustomGGUF by mradermacherUpdated 2025-12-23
Download on Hugging Face
Parameters13.2B
Context2K
Layers40
Architecturellama
Smallest quant0.0 GB
Quick answer

Custom KoLLM 13B v3 i1 needs about 15.2 GB of memory at Q4_K_M (a 8.0 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 25 quants, from 0.0 GB to 10.8 GB (Q6_K).

Custom KoLLM 13B v3 i1 – 13.2B parameter LLaMA‑based model

Custom KoLLM 13B v3 i1 is a 13.2B parameter auto‑regressive language model based on the LLaMA architecture. It was trained on the Ko-various-dataset and released under a cc‑by‑nc‑sa‑4.0 license. The model supports a 2048 token context window.

Good at

  • Text generation in Korean and English
  • Fine‑tuned conversational responses
  • Domain‑specific knowledge from Ko-various-dataset

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • cc‑by‑nc‑sa‑4.0 license restricts commercial use

Best for

  • Chatbot prototypes
  • Content drafting
  • Research prototyping

Who it’s for. Developers and researchers who need a Korean‑English LLaMA‑based model for non‑commercial projects. The model is suitable for experimentation and small‑scale deployment.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 2.2 GB
Fits Get file →
IQ1_S3.0 GB 5.2 GB
Fits Get file →
IQ1_M3.2 GB 5.4 GB
Fits Get file →
IQ2_XXS3.6 GB 5.8 GB
Fits Get file →
IQ2_XS4.0 GB 6.1 GB
Fits Get file →
IQ2_S4.3 GB 6.5 GB
Fits Get file →
Q2_K_S4.5 GB 6.7 GB
Fits Get file →
IQ2_M4.6 GB 6.8 GB
Fits Get file →
Q2_K4.9 GB 7.1 GB
Fits Get file →
IQ3_XXS5.0 GB 7.2 GB
Tight Get file →
IQ3_XS5.5 GB 7.6 GB
Tight Get file →
IQ3_S5.8 GB 7.9 GB
Tight Get file →
Q3_K_S5.8 GB 7.9 GB
Tight Get file →
IQ3_M6.1 GB 8.3 GB
Too big Get file →
Q3_K_M6.4 GB 8.6 GB
Too big Get file →
Q3_K_L7.0 GB 9.2 GB
Too big Get file →
IQ4_XS7.1 GB 9.2 GB
Too big Get file →
IQ4_NL7.5 GB 9.6 GB
Too big Get file →
Q4_07.5 GB 9.7 GB
Too big Get file →
Q4_K_S7.5 GB 9.7 GB
Too big Get file →
Q4_K_M8.0 GB 10.1 GB
Too big Get file →
Q4_18.3 GB 10.5 GB
Too big Get file →
Q5_K_S9.1 GB 11.3 GB
Too big Get file →
Q5_K_M9.3 GB 11.5 GB
Too big Get file →
Q6_K10.8 GB 13.0 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 2.97 GB, memory 10.2 GB) or IQ1_M (3.21 GB, 10.4 GB). For 12 GB VRAM, Q2_K (4.94 GB, 12.1 GB) or IQ3_S (5.75 GB, 13 GB) are suitable. Higher memory budgets allow Q4_K_M (7.97 GB, 15.2 GB) or Q5_K_M (9.34 GB, 16.6 GB).

What GPU do you need for Custom KoLLM 13B v3 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: 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 the main file (0.0 GB file, about 7.2 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ2_M (4.6 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_1 (8.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (10.8 GB file, about 18.0 GB in use).

Which Custom KoLLM 13B v3 i1 quant should you choose?

Q4_K_M is the usual starting point for Custom KoLLM 13B v3 i1: it balances file size and quality well. Here it is a 8.0 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
Parameters13.2B
Layers40
Trained context2,048 tokens
KV cache (fp16)800 KB per token

Source

Quantized bymradermacher
FamilyCustom
Downloads (HF)967
Last updated2025-12-23

Frequently asked questions about Custom KoLLM 13B v3 i1

How much VRAM does Custom KoLLM 13B v3 i1 need?

About 15.2 GB at Q4_K_M with an 8K context window. That is the 8.0 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 Custom KoLLM 13B v3 i1 on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Custom KoLLM 13B v3 i1 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 4.0 GB, IQ2_S is 4.3 GB and 19 more.

What context length does Custom KoLLM 13B v3 i1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 6.7 GB at 8K and 1.7 GB at 2K.

Where can I download Custom KoLLM 13B v3 i1 GGUF?

The files are on Hugging Face in the mradermacher/Custom-KoLLM-13B-v3-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 Custom KoLLM 13B v3 i1 use?

Hugging Face lists the license as cc-by-nc-sa-4.0. 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?

The smallest quant that fits 8 GB VRAM is IQ1_S, which uses 10.2 GB of memory at 8k context. It will not fit without swapping.

Does the model support vision tasks?

No, the model is purely text‑based and has no vision capabilities.

Is the model free for commercial use?

No, the cc‑by‑nc‑sa‑4.0 license prohibits commercial use without permission.

Other GGUFs of Custom-KoLLM-13B-v3

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Custom models

All Custom →

Other medium models

All medium models →