SO

Solar Ko Recovery 11B

SolarGGUF by beomiUpdated 2024-11-25
Download on Hugging Face
Parameters11B
Context4K
Layers48
Architecturellama
Smallest quant11.7 GB
Quick answer

Solar Ko Recovery 11B needs about 13.8 GB of memory at Q8_0 (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU.

Solar Ko Recovery 11B is a 11B-parameter Solar model in GGUF format, quantized by beomi. Its trained context length is 4K tokens. The repository has 1 quant file, from 11.7 GB (Q8_0) to 11.7 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_011.7 GB 13.0 GB
Too big Get file →

What GPU do you need for Solar Ko Recovery 11B?

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 Q8_0 (11.7 GB file, about 13.8 GB in use).

Which Solar Ko Recovery 11B quant should you choose?

Q8_0 (11.7 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters11B
Layers48
Trained context4,096 tokens
KV cache (fp16)192 KB per token

Source

Quantized bybeomi
FamilySolar
Licenseapache-2.0
Downloads (HF)13
Last updated2024-11-25

Frequently asked questions about Solar Ko Recovery 11B

How much VRAM does Solar Ko Recovery 11B need?

About 13.8 GB at Q8_0 with an 8K context window. That is the 11.7 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 Recovery 11B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.8 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Solar Ko Recovery 11B GGUF?

It depends on the quant: Q8_0 is 11.7 GB.

What context length does Solar Ko Recovery 11B 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 Ko Recovery 11B GGUF?

The files are on Hugging Face in the beomi/Solar-Ko-Recovery-11B-Q8_0-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 Recovery 11B 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-Recovery-11B

Similar models

Browse all →

More from beomi

All by beomi →

More Solar models

All Solar →

Other medium models

All medium models →