SO

SOLAR 19.2B Instruct v1.0 Q4 K M

SolarGGUF by bingbortUpdated 2024-04-15
Download on Hugging Face
Parameters18.6B
Context4K
Layers84
Architecturellama
Smallest quant11.2 GB
Quick answer

SOLAR 19.2B Instruct v1.0 Q4 K M needs about 14.5 GB of memory at Q4_K_M (a 11.2 GB file) with an 8K context window, so it fits on a 16 GB GPU.

SOLAR 19.2B Instruct v1.0 Q4 K M is a 18.6B-parameter Solar model in GGUF format, quantized by bingbort. Its trained context length is 4K tokens. The repository has 1 quant file, from 11.2 GB (Q4_K_M) to 11.2 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M11.2 GB 13.1 GB
Too big Get file →

What GPU do you need for SOLAR 19.2B Instruct v1.0 Q4 K M?

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: the best quant that fits is Q4_K_M (11.2 GB file, about 14.5 GB in use).

Which SOLAR 19.2B Instruct v1.0 Q4 K M quant should you choose?

Q4_K_M is the usual starting point for SOLAR 19.2B Instruct v1.0 Q4 K M: it balances file size and quality well. Here it is a 11.2 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters18.6B
Layers84
Trained context4,096 tokens
KV cache (fp16)336 KB per token

Source

Quantized bybingbort
FamilySolar
Licensecc
Downloads (HF)17
Last updated2024-04-15

Frequently asked questions about SOLAR 19.2B Instruct v1.0 Q4 K M

How much VRAM does SOLAR 19.2B Instruct v1.0 Q4 K M need?

About 14.5 GB at Q4_K_M with an 8K context window. That is the 11.2 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 19.2B Instruct v1.0 Q4 K M on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of SOLAR 19.2B Instruct v1.0 Q4 K M GGUF?

It depends on the quant: Q4_K_M is 11.2 GB.

What context length does SOLAR 19.2B Instruct v1.0 Q4 K M support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 2.8 GB at 8K and 1.4 GB at 4K.

Where can I download SOLAR 19.2B Instruct v1.0 Q4 K M GGUF?

The files are on Hugging Face in the bingbort/SOLAR-19.2B-Instruct-v1.0-Q4_K_M-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 19.2B Instruct v1.0 Q4 K M use?

Hugging Face lists the license as cc. 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 from bingbort

All by bingbort →

More Solar models

All Solar →

Other medium models

All medium models →