Imbue Models by Imbue
Last refreshed 2026-05-19. Next refresh: weekly.
Details
About
Imbue, an AI research company previously known as Generally Intelligent, focuses on creating advanced AI systems that excel in reasoning and coding. A significant milestone for Imbue is the development of a large language model with 70 billion parameters, optimized specifically for reasoning tasks—a complex area for current AI models 12. This model has been fine-tuned using various multiple-choice reasoning benchmarks to enhance its performance. Imbue aims to apply these foundation models towards the creation of practical AI agents that not only reason but also code, ultimately empowering users to construct custom AI solutions. Although details about a broader family of LLMs from Imbue are limited, their research strongly suggests a dedication to robust reasoning capabilities in AI 2.
Decision facts
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
Use when the workload needs 4k context and 70B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Imbue 70B | Use when the workload needs 4k context and 70B parameters. | 2024-08 | 4k context70B parameters | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Imbue 70B | 2024-08 | 4k | 70B |