SO

SOLAR 10.7B v1.0 Instruct

SolarGGUF by myunghoonseUpdated 2024-08-11
Download on Hugging Face
Parameters10.7B
Context4K
Layers48
Architecturellama
Smallest quant21.5 GB
Quick answer

SOLAR 10.7B v1.0 Instruct needs about 23.6 GB of memory at its main file (a 21.5 GB file) with an 8K context window, so it fits on a 24 GB GPU.

SOLAR 10.7B v1.0 Instruct is a 10.7B-parameter Solar model in GGUF format, quantized by myunghoonse. Its trained context length is 4K tokens. The repository has 1 quant file, from 21.5 GB to 21.5 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—21.5 GB 22.8 GB
Too big Get file →

What GPU do you need for SOLAR 10.7B v1.0 Instruct?

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: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: the best quant that fits is the main file (21.5 GB file, about 23.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bymyunghoonse
FamilySolar
Licenseapache-2.0
Downloads (HF)5
Last updated2024-08-11

Frequently asked questions about SOLAR 10.7B v1.0 Instruct

How much VRAM does SOLAR 10.7B v1.0 Instruct need?

About 23.6 GB at its main file with an 8K context window. That is the 21.5 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 10.7B v1.0 Instruct on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 23.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SOLAR 10.7B v1.0 Instruct GGUF?

It depends on the quant: file is 21.5 GB.

What context length does SOLAR 10.7B v1.0 Instruct 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 SOLAR 10.7B v1.0 Instruct GGUF?

The files are on Hugging Face in the myunghoonse/SOLAR-10.7B-v1.0-Instruct-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 10.7B v1.0 Instruct 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.

Similar models

Browse all →

More Solar models

All Solar →

Other medium models

All medium models →