NU

numnim3_beta_16bit_GGUF

NumnimGGUF by krittapolUpdated 2024-07-02
Download on Hugging Face
Parameters7.27B
Context32K
Layers32
Architecturellama
Smallest quant14.5 GB
Quick answer

numnim3_beta_16bit_GGUF needs about 16.1 GB of memory at F16 (a 14.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.

numnim3_beta_16bit_GGUF is a 7.27B-parameter Numnim model in GGUF format, quantized by krittapol. Its trained context length is 32K tokens. The repository has 1 quant file, from 14.5 GB (F16) to 14.5 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F1614.5 GB 16.1 GB
Too big Get file →

What GPU do you need for numnim3_beta_16bit_GGUF?

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: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).

Which numnim3_beta_16bit_GGUF quant should you choose?

F16 (14.5 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
Parameters7.27B
Layers32
Trained context32,768 tokens
KV cache (fp16)128 KB per token

Source

Quantized bykrittapol
FamilyNumnim
Downloads (HF)23
Last updated2024-07-02

Frequently asked questions about numnim3_beta_16bit_GGUF

How much VRAM does numnim3_beta_16bit_GGUF need?

About 16.1 GB at F16 with an 8K context window. That is the 14.5 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 numnim3_beta_16bit_GGUF on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 16.1 GB, so you would need a larger GPU or CPU offloading.

What is the file size of numnim3_beta_16bit_GGUF GGUF?

It depends on the quant: F16 is 14.5 GB.

What context length does numnim3_beta_16bit_GGUF support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.

Where can I download numnim3_beta_16bit_GGUF GGUF?

The files are on Hugging Face in the krittapol/numnim3_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 small models

All small models →