LLM Reference

GigaChat Models by Gigachat (Sberbank)

3 models2023Up to 32k ctx

About

GigaChat is an advanced large language model (LLM) developed by Sberbank, renowned for its multifaceted capabilities in the realm of artificial intelligence. This multimodal AI chatbot is adept at a range of tasks, including responding to queries, generating coherent text, writing code, and creating images. Distinctively, GigaChat excels in Russian language communication, aiming to provide superior interactions compared to its foreign counterparts. Built on the NEural Omnimodal Network with Knowledge-Awareness (NeONKA) foundation, it integrates various neural networks and emphasizes human feedback to enhance its performance. Initially launched for closed beta testing, it is intended to serve a diverse audience comprising students, researchers, and businesses. While specific technical details are scarce, it is noted for leveraging a model architecture consisting of approximately 13 billion parameters.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

3 in view

Use when the workload needs 8k context.

2023-068k context

Use when the workload needs 32k context.

2023-0632k context

Use when the workload needs 8k context.

2023-068k context

Release Timeline

1 release group
2023-06
3 current
GigaChat Lite
8k context
Current
GigaChat Lite+
32k context
Current
GigaChat Pro
8k context
Current

Specifications(3 models)

GigaChat model specifications comparison
ModelReleasedContext
GigaChat Pro2023-068k
GigaChat Lite+2023-0632k
GigaChat Lite2023-068k

Frequently Asked Questions

What is GigaChat used for?
GigaChat is used for coding and chatbot and role-playing use cases. The family description and listed model capabilities point to those workloads as the best fit.
How does GigaChat compare to Claude 3?
GigaChat by Gigachat (Sberbank) is strongest where you need coding, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. GigaChat has 3 listed variants and reaches up to 32k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
Which GigaChat model should I use?
If price is the main constraint, use the pricing table first because GigaChat does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate GigaChat Lite+ with 32k context.

Models(3)