BL

BlackSheep 5B Q5 K S

BlacksheepGGUF by fuzzy-mittenzUpdated 2024-12-19
Download on Hugging Face
Parameters5.02B
Context128K
Layers42
Architecturellama
Smallest quant3.5 GB
Quick answer

BlackSheep 5B Q5 K S needs about 5.4 GB of memory at Q5_K_S (a 3.5 GB file) with an 8K context window, so it fits on a 6 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.

BlackSheep 5B Q5 K S is a 5.02B-parameter Blacksheep model in GGUF format, quantized by fuzzy-mittenz. Its trained context length is 128K tokens. The repository has 1 quant file, from 3.5 GB (Q5_K_S) to 3.5 GB (Q5_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q5_K_S3.5 GB 5.4 GB
Fits Get file →

What GPU do you need for BlackSheep 5B Q5 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: the best quant that fits is Q5_K_S (3.5 GB file, about 5.4 GB in use).

Which BlackSheep 5B Q5 K S quant should you choose?

Q5_K_S (3.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters5.02B
Layers42
Trained context131,072 tokens
KV cache (fp16)168 KB per token

Source

Quantized byfuzzy-mittenz
Downloads (HF)9
Last updated2024-12-19

Frequently asked questions about BlackSheep 5B Q5 K S

How much VRAM does BlackSheep 5B Q5 K S need?

About 5.4 GB at Q5_K_S with an 8K context window. That is the 3.5 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 BlackSheep 5B Q5 K S on an 8 GB GPU?

Yes, with Q5_K_S: the 3.5 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of BlackSheep 5B Q5 K S GGUF?

It depends on the quant: Q5_K_S is 3.5 GB.

What context length does BlackSheep 5B Q5 K S support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.

Where can I download BlackSheep 5B Q5 K S GGUF?

The files are on Hugging Face in the fuzzy-mittenz/BlackSheep-5B-Q5_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 BlackSheep-5B

Similar models

Browse all →

More from fuzzy-mittenz

All by fuzzy-mittenz →

More Blacksheep models

All Blacksheep →

Other small models

All small models →