FireLLaVA Models by Fireworks AI
Last refreshed 2026-05-19. Next refresh: weekly.
Details
About
FireLLaVA is a family of vision-language models (VLMs) innovatively developed by Fireworks AI. Built on the LLaVA architecture, these models are celebrated for their open-source nature, released under the Llama 2 Community License, making them the first commercially permissive LLaVA models available 58. Unlike previous VLMs such as the original LLaVA, which faced commercial restrictions due to proprietary training data, FireLLaVA models utilize open-source instruction-following data, achieving performance on par with or surpassing prior benchmarks 58. Notably, the FireLLaVA-13b model, trained in December 2023 and available on Hugging Face, is tailored for single-image inputs while also supporting multi-image and multi-prompt generation 8.
Decision facts
- Best fit
- coding
- Capability starting point
- FireLLaVA 13B with 4k context
- Lowest tracked input
- FireLLaVA 13B · $0.9/1M · Fireworks AI
- Closest related family
- Fireworks Functions
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 13B parameters.
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| FireLLaVA 13B | Use when the workload needs 4k context and 13B parameters. | 2024-04 | 4k context13B parameters | Current |
Release Timeline
1 release groupSpecifications(1 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| FireLLaVA 13B | 2024-04 | 4k | 13B |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| FireLLaVA 13B | Fireworks AI | $0.9 | $0.9 | Serverless |
