BL

Bloom 3b Zh

BloomGGUF by d8912046Updated 2025-01-20
Download on Hugging Face
Parameters3.64B
Context2K
Layers30
Architecturebloom
Smallest quant2.2 GB
Quick answer

Bloom 3b Zh needs about 5.3 GB of memory at Q4_K_S (a 2.2 GB file) with an 8K context window, so it fits on a 6 GB GPU.

Bloom 3b Zh is a 3.64B-parameter Bloom model in GGUF format, quantized by d8912046. Its trained context length is 2K tokens. The repository has 1 quant file, from 2.2 GB (Q4_K_S) to 2.2 GB (Q4_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_S2.2 GB 3.4 GB
Fits Get file →

What GPU do you need for Bloom 3b Zh?

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 Q4_K_S (2.2 GB file, about 5.3 GB in use).

Which Bloom 3b Zh quant should you choose?

Q4_K_S (2.2 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
Parameters3.64B
Layers30
Trained context2,048 tokens
KV cache (fp16)300 KB per token

Source

Quantized byd8912046
FamilyBloom
Downloads (HF)13
Last updated2025-01-20

Frequently asked questions about Bloom 3b Zh

How much VRAM does Bloom 3b Zh need?

About 5.3 GB at Q4_K_S with an 8K context window. That is the 2.2 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 Bloom 3b Zh on an 8 GB GPU?

Yes, with Q4_K_S: the 2.2 GB file needs about 5.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Bloom 3b Zh GGUF?

It depends on the quant: Q4_K_S is 2.2 GB.

What context length does Bloom 3b Zh support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 2.5 GB at 8K and 0.6 GB at 2K.

Where can I download Bloom 3b Zh GGUF?

The files are on Hugging Face in the d8912046/bloom-3b-zh-Q4_K_S-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Bloom 3b Zh use?

Hugging Face lists the license as bigscience-bloom-rail-1.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Similar models

Browse all →

More from d8912046

All by d8912046 →

More Bloom models

All Bloom →

Other small models

All small models →