BL

Bigscience.Bloomz P3

BloomzGGUF by csabakecskemetiUpdated 2025-05-25
Download on Hugging Face
Parameters176B
Context2K
Layers70
Architecturebloom
Smallest quant67.0 GB
Quick answer

Bigscience.Bloomz P3 needs about 146.1 GB of memory at Q4_K_M (a 112.7 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 67.0 GB (Q2_K) to 112.7 GB (Q4_K_M).

Bigscience.Bloomz P3 is a 176B-parameter Bloomz model in GGUF format, quantized by csabakecskemeti. Its trained context length is 2K tokens. The repository has 3 quant files, from 67.0 GB (Q2_K) to 112.7 GB (Q4_K_M).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K67.0 GB (5 parts) 75.7 GB
Too big Get file →
Q3_K_S77.2 GB (6 parts) 85.9 GB
Too big Get file →
Q4_K_M112.7 GB (9 parts) 121.4 GB
Too big Get file →

What GPU do you need for Bigscience.Bloomz P3?

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: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Bigscience.Bloomz P3 quant should you choose?

Q4_K_M is the usual starting point for Bigscience.Bloomz P3: it balances file size and quality well. Here it is a 112.7 GB file.

If memory is tight, the smallest file is Q2_K at 67.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturebloom
Parameters176B
Layers70
Trained context2,048 tokens
KV cache (fp16)3920 KB per token

Source

Quantized bycsabakecskemeti
FamilyBloomz
Downloads (HF)55
Last updated2025-05-25

Frequently asked questions about Bigscience.Bloomz P3

How much VRAM does Bigscience.Bloomz P3 need?

About 146.1 GB at Q4_K_M with an 8K context window. That is the 112.7 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 Bigscience.Bloomz P3 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 100.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Bigscience.Bloomz P3 GGUF?

It depends on the quant: Q2_K is 67.0 GB, Q3_K_S is 77.2 GB, Q4_K_M is 112.7 GB.

What context length does Bigscience.Bloomz P3 support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 32.9 GB at 8K and 8.2 GB at 2K.

Where can I download Bigscience.Bloomz P3 GGUF?

The files are on Hugging Face in the csabakecskemeti/bigscience.bloomz-p3-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 Bigscience.Bloomz P3 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.

Other GGUFs of bloomz-p3

Similar models

Browse all →

More from csabakecskemeti

All by csabakecskemeti →

More Bloomz models

All Bloomz →

Other large models

All large models →