SO

SOLAR KO Various v0.1

SolarGGUF by mradermacherUpdated 2024-11-02
Download on Hugging Face
Parameters10.9B
Context2K
Layers48
Architecturellama
Smallest quant2.4 GB
Quick answer

SOLAR KO Various v0.1 needs about 8.7 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 24 quants, from 2.4 GB (IQ1_S) to 8.9 GB (Q6_K).

SOLAR KO Various v0.1 is a 10.9B-parameter Solar model in GGUF format, quantized by mradermacher. Its trained context length is 2K tokens. The repository has 24 quant files, from 2.4 GB (IQ1_S) to 8.9 GB (Q6_K).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ1_S2.4 GB 3.3 GB
Fits Get file →
IQ1_M2.6 GB 3.5 GB
Fits Get file →
IQ2_XXS3.0 GB 3.9 GB
Fits Get file →
IQ2_XS3.3 GB 4.2 GB
Fits Get file →
IQ2_S3.5 GB 4.4 GB
Fits Get file →
IQ2_M3.7 GB 4.6 GB
Fits Get file →
Q2_K4.1 GB 5.0 GB
Fits Get file →
IQ3_XXS4.2 GB 5.1 GB
Fits Get file →
IQ3_XS4.5 GB 5.4 GB
Fits Get file →
Q3_K_S4.7 GB 5.6 GB
Fits Get file →
IQ3_S4.8 GB 5.7 GB
Fits Get file →
IQ3_M4.9 GB 5.8 GB
Fits Get file →
Q3_K_M5.3 GB 6.2 GB
Fits Get file →
Q3_K_L5.7 GB 6.6 GB
Fits Get file →
IQ4_XS5.9 GB 6.8 GB
Fits Get file →
Q4_06.2 GB 7.1 GB
Fits Get file →
Q4_06.2 GB 7.1 GB
Fits Get file →
Q4_06.2 GB 7.1 GB
Fits Get file →
Q4_06.2 GB 7.1 GB
Fits Get file →
Q4_K_S6.2 GB 7.1 GB
Fits Get file →
Q4_K_M6.5 GB 7.4 GB
Tight Get file →
Q5_K_S7.5 GB 8.4 GB
Too big Get file →
Q5_K_M7.7 GB 8.6 GB
Too big Get file →
Q6_K8.9 GB 9.8 GB
Too big Get file →

What GPU do you need for SOLAR KO Various v0.1?

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: the best quant that fits is IQ2_M (3.7 GB file, about 5.9 GB in use).
  • 8 GB VRAM: the best quant that fits is IQ4_XS (5.9 GB file, about 8.0 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (8.9 GB file, about 11.0 GB in use).

Which SOLAR KO Various v0.1 quant should you choose?

Q4_K_M is the usual starting point for SOLAR KO Various v0.1: it balances file size and quality well. Here it is a 6.5 GB file.

If memory is tight, the smallest file is IQ1_S at 2.4 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
Parameters10.9B
Layers48
Trained context2,048 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymradermacher
FamilySolar
Licenseapache-2.0
Downloads (HF)26
Last updated2024-11-02

Frequently asked questions about SOLAR KO Various v0.1

How much VRAM does SOLAR KO Various v0.1 need?

About 8.7 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 SOLAR KO Various v0.1 on an 8 GB GPU?

Yes, with IQ4_XS: the 5.9 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of SOLAR KO Various v0.1 GGUF?

It depends on the quant: IQ1_S is 2.4 GB, IQ1_M is 2.6 GB, IQ2_XXS is 3.0 GB, IQ2_XS is 3.3 GB, IQ2_S is 3.5 GB, IQ2_M is 3.7 GB and 18 more.

What context length does SOLAR KO Various v0.1 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 1.6 GB at 8K and 0.4 GB at 2K.

Where can I download SOLAR KO Various v0.1 GGUF?

The files are on Hugging Face in the mradermacher/SOLAR-KO-various-v0.1-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 SOLAR KO Various v0.1 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.

Other GGUFs of SOLAR-KO-various-v0.1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Solar models

All Solar →

Other medium models

All medium models →