NE

NeverSleep SynthiAirMix 11B special quant

NeversleepGGUF by nistenUpdated 2023-12-31
Download on Hugging Face
Parameters10.7B
Context32K
Layers48
Architecturellama
Smallest quant7.0 GB
Quick answer

NeverSleep SynthiAirMix 11B special quant needs about 12.4 GB of memory at its main file (a 10.3 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 7.0 GB to 12.6 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 6.4 GB.

NeverSleep SynthiAirMix 11B special quant is a 10.7B-parameter Neversleep model in GGUF format, quantized by nisten. Its trained context length is 32K tokens. The repository has 3 quant files, from 7.0 GB to 12.6 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—7.0 GB 9.1 GB
Too big Get file →
—10.3 GB 12.4 GB
Too big Get file →
—12.6 GB 14.7 GB
Too big Get file →

What GPU do you need for NeverSleep SynthiAirMix 11B special quant?

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: the best quant that fits is the main file (7.0 GB file, about 9.1 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (12.6 GB file, about 14.7 GB in use).

Which NeverSleep SynthiAirMix 11B special quant quant should you choose?

If memory is tight, the smallest file is the first one in the table at 7.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters10.7B
Layers48
Trained context32,768 tokens
KV cache (fp16)192 KB per token

Source

Quantized bynisten
Licensemit
Downloads (HF)28
Last updated2023-12-31

Frequently asked questions about NeverSleep SynthiAirMix 11B special quant

How much VRAM does NeverSleep SynthiAirMix 11B special quant need?

About 12.4 GB at its main file with an 8K context window. That is the 10.3 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 NeverSleep SynthiAirMix 11B special quant on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NeverSleep SynthiAirMix 11B special quant GGUF?

It depends on the quant: file is 7.0 GB, file is 10.3 GB, file is 12.6 GB.

What context length does NeverSleep SynthiAirMix 11B special quant support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.4 GB at 32K.

Where can I download NeverSleep SynthiAirMix 11B special quant GGUF?

The files are on Hugging Face in the nisten/NeverSleep-SynthiAirMix-11B-special-quant-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 NeverSleep SynthiAirMix 11B special quant use?

Hugging Face lists the license as mit. 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 nisten

All by nisten →

More Neversleep models

All Neversleep →

Other medium models

All medium models →