BL

bloomz 560m

BloomzGGUF by prodm93Updated 2023-11-16
Download on Hugging Face
Parameters816M
Context2K
Layers24
Architecturebloom
Smallest quant0.5 GB
Quick answer

bloomz 560m needs about 1.8 GB of memory at Q4_K_S (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.5 GB (Q4_K_S) to 0.6 GB (Q5_K_M).

bloomz 560m is a 816M-parameter Bloomz model in GGUF format, quantized by prodm93. Its trained context length is 2K tokens. The repository has 2 quant files, from 0.5 GB (Q4_K_S) to 0.6 GB (Q5_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S0.5 GB 1.2 GB
Fits Get file →
Q5_K_M0.6 GB 1.3 GB
Fits Get file →

What GPU do you need for bloomz 560m?

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: the best quant that fits is Q5_K_M (0.6 GB file, about 1.9 GB in use).

Which bloomz 560m quant should you choose?

Q4_K_S (0.5 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

Architecturebloom
Parameters816M
Layers24
Trained context2,048 tokens
KV cache (fp16)96 KB per token

Source

Quantized byprodm93
FamilyBloomz
Downloads (HF)6
Last updated2023-11-16

Frequently asked questions about bloomz 560m

How much VRAM does bloomz 560m need?

About 1.8 GB at Q4_K_S with an 8K context window. That is the 0.5 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 bloomz 560m on an 8 GB GPU?

Yes, with Q5_K_M: the 0.6 GB file needs about 1.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of bloomz 560m GGUF?

It depends on the quant: Q4_K_S is 0.5 GB, Q5_K_M is 0.6 GB.

What context length does bloomz 560m support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.8 GB at 8K and 0.2 GB at 2K.

Where can I download bloomz 560m GGUF?

The files are on Hugging Face in the prodm93/bloomz-560m-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 prodm93

All by prodm93 →

More Bloomz models

All Bloomz →

Other tiny models

All tiny models →