LLM Reference

BLOOMZ Models by BigScience

BigScienceBigScience RAIL LicenseOpen weights
This model family is considered obsolete. Consider newer alternatives in Related Model Families below.
6 models2022Up to 2k ctx

Last refreshed 2026-05-19. Next refresh: weekly.

Details

ResearcherBigScience
Commercial useCommercial use: conditional
Models6
Released2022
Max context2k

About

The BLOOMZ model family, an innovation from the BigScience workshop, offers an array of multilingual models that excel in instruction following across diverse languages without necessitating additional training 123. These advanced models are fine-tuned iterations of the BLOOM and mT5 architectures, leveraging the comprehensive cross-lingual task mixture (xP3) dataset for enhanced multilingual capabilities 123. BLOOMZ's flexibility is evident in its range of sizes, from 300 million to a substantial 176 billion parameters, to accommodate various computational needs 124. Moreover, the bloomz-mt variants are specifically fine-tuned to handle non-English prompts using the xP3mt dataset, further solidifying their prowess in cross-lingual generalization and task diversity, including machine translation, question answering, and text generation 14.

Decision facts

Best fit
codingchatbot and role-playing use cases
Capability starting point
BLOOMZ 176B with 2k context
Lowest tracked input
Not tracked
Closest related family
MT0

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

6 in view

Use when the workload needs 2k context and 176B parameters.

2022-072k context176B parameters

Use when the workload needs 2k context and 7.1B parameters.

2022-072k context7.1B parameters
BLOOMZ 3BCurrent

Use when the workload needs 2k context and 3B parameters.

2022-072k context3B parameters

Use when the workload needs 2k context and 1.7B parameters.

2022-072k context1.7B parameters

Use when the workload needs 2k context and 1.1B parameters.

2022-072k context1.1B parameters

Use when the workload needs 2k context and 560M parameters.

2022-072k context560M parameters

Release Timeline

1 release group
2022-07
6 current
BLOOMZ 1.1B
2k context1.1B parameters
Current
BLOOMZ 1.7B
2k context1.7B parameters
Current
BLOOMZ 176B
2k context176B parameters
Current
BLOOMZ 3B
2k context3B parameters
Current
BLOOMZ 560M
2k context560M parameters
Current
BLOOMZ 7.1B
2k context7.1B parameters
Current

Specifications(6 models)

BLOOMZ model specifications comparison
ModelReleasedContextParameters
BLOOMZ 176B2022-072k176B
BLOOMZ 7.1B2022-072k7.1B
BLOOMZ 3B2022-072k3B
BLOOMZ 1.7B2022-072k1.7B
BLOOMZ 1.1B2022-072k1.1B
BLOOMZ 560M2022-072k560M