NU

numnim7 beta q4 k m

NumnimGGUF by krittapolUpdated 2024-08-27
Download on Hugging Face
Parameters6.81B
Context4K
Layers32
Architecturellama
Smallest quant4.1 GB
Quick answer

numnim7 beta q4 k m needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 4.1 GB (Q4_K_M) to 13.6 GB (F16).

numnim7 beta q4 k m is a 6.81B-parameter Numnim model in GGUF format, quantized by krittapol. Its trained context length is 4K tokens. The repository has 2 quant files, from 4.1 GB (Q4_K_M) to 13.6 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M4.1 GB 6.8 GB
Fits Get file →
F1613.6 GB 16.3 GB
Too big Get file →

What GPU do you need for numnim7 beta q4 k m?

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 Q4_K_M (4.1 GB file, about 8.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (4.1 GB file, about 8.9 GB in use).
  • 24 GB VRAM: the best quant that fits is F16 (13.6 GB file, about 18.4 GB in use).

Which numnim7 beta q4 k m quant should you choose?

Q4_K_M is the usual starting point for numnim7 beta q4 k m: it balances file size and quality well. Here it is a 4.1 GB file.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters6.81B
Layers32
Trained context4,096 tokens
KV cache (fp16)512 KB per token

Source

Quantized bykrittapol
FamilyNumnim
Downloads (HF)9
Last updated2024-08-27

Frequently asked questions about numnim7 beta q4 k m

How much VRAM does numnim7 beta q4 k m need?

About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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 numnim7 beta q4 k m on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of numnim7 beta q4 k m GGUF?

It depends on the quant: Q4_K_M is 4.1 GB, F16 is 13.6 GB.

What context length does numnim7 beta q4 k m support?

The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.

Where can I download numnim7 beta q4 k m GGUF?

The files are on Hugging Face in the krittapol/numnim7_beta_q4_k_m 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 →