NE

NeMoria 21b Q4 K S

NemoriaGGUF by mheftie296Updated 2024-07-31
Download on Hugging Face
Parameters20.4B
Context1000K
Layers70
Architecturellama
Smallest quant11.7 GB
Quick answer

NeMoria 21b Q4 K S needs about 14.6 GB of memory at Q4_K_S (a 11.7 GB file) with an 8K context window, so it fits on a 16 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 9.4 GB.

NeMoria 21b Q4 K S is a 20.4B-parameter Nemoria model in GGUF format, quantized by mheftie296. Its trained context length is 1000K tokens. The repository has 1 quant file, from 11.7 GB (Q4_K_S) to 11.7 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S11.7 GB 14.6 GB
Too big Get file →

What GPU do you need for NeMoria 21b Q4 K S?

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_S (11.7 GB file, about 14.6 GB in use).

Which NeMoria 21b Q4 K S quant should you choose?

Q4_K_S (11.7 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters20.4B
Layers70
Trained context1,024,000 tokens
KV cache (fp16)280 KB per token

Source

Quantized bymheftie296
FamilyNemoria
Downloads (HF)5
Last updated2024-07-31

Frequently asked questions about NeMoria 21b Q4 K S

How much VRAM does NeMoria 21b Q4 K S need?

About 14.6 GB at Q4_K_S 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 NeMoria 21b Q4 K S on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 14.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NeMoria 21b Q4 K S GGUF?

It depends on the quant: Q4_K_S is 11.7 GB.

What context length does NeMoria 21b Q4 K S support?

The GGUF header lists a trained context length of 1,024,000 tokens (1000K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.4 GB at 32K.

Where can I download NeMoria 21b Q4 K S GGUF?

The files are on Hugging Face in the mheftie296/NeMoria-21b-Q4_K_S-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of NeMoria-21b

Similar models

Browse all →

More Nemoria models

All Nemoria →

Other medium models

All medium models →