Chronos Llama 1 Models by Elinas
Last refreshed 2026-05-19. Next refresh: weekly.
Details
Links
HuggingFaceAbout
The Chronos family of LLMs, built on the Llama 1 architecture, excels in generating creative text tailored for chat, roleplay, and storywriting applications 456. These models are celebrated for their ability to produce lengthy and coherent outputs, a capability enhanced by training on human-generated content 411. Beyond their creative prowess, Chronos models also handle tasks like simple reasoning and coding 411. Versions differ in parameters and quantization methods, affecting their performance and resource need, with options like FP16 and 4-bit quantization available to balance accuracy against computational demands 235. Alpaca prompt format is commonly used for optimal results 456, and specific models like Chronos Hermes incorporate mergers for enhanced capabilities 7913.
Decision facts
- Best fit
- coding
- Capability starting point
- Chronos 33B with 4k context
- Lowest tracked input
- Not tracked
- Closest related family
- Chronos Llama 2
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 33B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Chronos 33B | Use when the workload needs 4k context and 33B parameters. | 2023-02 | 4k context33B parameters | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Chronos 33B | 2023-02 | 4k | 33B |


