SO

KULLM3

SolarGGUF by QuantFactoryUpdated 2024-09-09
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant4.0 GB
Quick answer

KULLM3 needs about 8.6 GB of memory at Q4_K_M (a 6.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 14 quants, from 4.0 GB (Q2_K) to 11.4 GB (Q8_0).

KULLM3 – 10.7B Korean‑English instruction‑following LLM

KULLM3 is a 10.7B parameter model based on upstage/SOLAR‑10.7B‑v1.0. It is fine‑tuned for instruction following and fluent chat in Korean and English. The model is released under the Apache‑2.0 license.

Good at

  • Instruction following
  • Korean‑English dialogue
  • Fine‑tuning ready

Limits

  • No vision support
  • Requires fine‑tuning for chat
  • Context limited to 4096 tokens

Best for

  • Fine‑tuning Korean instruction datasets
  • Chatbot prototypes
  • Language research

Who it’s for. Developers and researchers who need a Korean‑English LLM that can be fine‑tuned for specific tasks. The model is suitable for building chat applications or conducting NLP experiments.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K4.0 GB 5.3 GB
Fits Get file →
Q3_K_S4.7 GB 6.0 GB
Fits Get file →
Q3_K_M5.2 GB 6.5 GB
Fits Get file →
Q3_K_L5.7 GB 7.0 GB
Fits Get file →
Q4_06.1 GB 7.4 GB
Tight Get file →
Q4_K_S6.1 GB 7.4 GB
Tight Get file →
Q4_K_M6.5 GB 7.8 GB
Tight Get file →
Q4_16.7 GB 8.0 GB
Too big Get file →
Q5_07.4 GB 8.7 GB
Too big Get file →
Q5_K_S7.4 GB 8.7 GB
Too big Get file →
Q5_K_M7.6 GB 8.9 GB
Too big Get file →
Q5_18.1 GB 9.4 GB
Too big Get file →
Q6_K8.8 GB 10.1 GB
Too big Get file →
Q8_011.4 GB 12.7 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_M (6.46 GB file, ~8.6 GB memory). For 12 GB VRAM, Q5_K_M (7.6 GB file, ~9.7 GB memory) is a good balance. Larger VRAM allows Q6_K (8.81 GB file, ~10.9 GB memory).

What GPU do you need for KULLM3?

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 Q3_K_L (5.7 GB file, about 7.8 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.8 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q8_0 (11.4 GB file, about 13.5 GB in use).

Which KULLM3 quant should you choose?

Q4_K_M is the usual starting point for KULLM3: it balances file size and quality well. Here it is a 6.5 GB file.

The Q8_0 file is 11.4 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 4.0 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
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized byQuantFactory
FamilySolar
Licenseapache-2.0
Downloads (HF)1,659
Last updated2024-09-09

Frequently asked questions about KULLM3

How much VRAM does KULLM3 need?

About 8.6 GB at Q4_K_M with an 8K context window. That is the 6.5 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 KULLM3 on an 8 GB GPU?

Yes, with Q3_K_L: the 5.7 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of KULLM3 GGUF?

It depends on the quant: Q2_K is 4.0 GB, Q3_K_S is 4.7 GB, Q3_K_M is 5.2 GB, Q3_K_L is 5.7 GB, Q4_0 is 6.1 GB, Q4_K_S is 6.1 GB and 8 more.

What context length does KULLM3 support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.8 GB at 4K.

Where can I download KULLM3 GGUF?

The files are on Hugging Face in the QuantFactory/KULLM3-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 KULLM3 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 KULLM3 on 8 GB VRAM?

Yes, the Q4_K_M quantized file is 6.46 GB and requires about 8.6 GB VRAM at 8k context.

Does KULLM3 support vision tasks?

No, the model has no vision capabilities.

What license applies to KULLM3?

The model is released under the Apache‑2.0 license.

Other GGUFs of SOLAR-10.7B-v1.0

Similar models

Browse all →

More from QuantFactory

All by QuantFactory →

More Solar models

All Solar →

Other medium models

All medium models →