NU

numnim5 beta 16bit

NumnimGGUF by krittapolUpdated 2024-08-18
Download on Hugging Face
Parameters13.1B
Context4K
Layers40
Architecturellama
Smallest quant26.2 GB
Quick answer

numnim5 beta 16bit needs about 33.4 GB of memory at F16 (a 26.2 GB file) with an 8K context window, so it fits on a 48 GB GPU.

numnim5 beta 16bit is a 13.1B-parameter Numnim model in GGUF format, quantized by krittapol. Its trained context length is 4K tokens. The repository has 1 quant file, from 26.2 GB (F16) to 26.2 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1626.2 GB 30.1 GB
Too big Get file →

What GPU do you need for numnim5 beta 16bit?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: the best quant that fits is F16 (26.2 GB file, about 33.4 GB in use).

Which numnim5 beta 16bit quant should you choose?

F16 (26.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters13.1B
Layers40
Trained context4,096 tokens
KV cache (fp16)800 KB per token

Source

Quantized bykrittapol
FamilyNumnim
Downloads (HF)10
Last updated2024-08-18

Frequently asked questions about numnim5 beta 16bit

How much VRAM does numnim5 beta 16bit need?

About 33.4 GB at F16 with an 8K context window. That is the 26.2 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 numnim5 beta 16bit on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 33.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of numnim5 beta 16bit GGUF?

It depends on the quant: F16 is 26.2 GB.

What context length does numnim5 beta 16bit support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.

Where can I download numnim5 beta 16bit GGUF?

The files are on Hugging Face in the krittapol/numnim5_beta_16bit_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Similar models

Browse all →

More from krittapol

All by krittapol →

More Numnim models

All Numnim →

Other medium models

All medium models →