# Ling 3 Flash

> Ling 3 Flash is currently planned as a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token. The model is designed with token efficiency and production-scale agentic inference as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.

Provider: Fireworks · Type: LLM · State: Ready

model path: `accounts/fireworks/models/ling-3-flash`

[Deploy on demand](https://app.fireworks.ai/dashboard/deployments/create?baseModel=accounts/fireworks/models/ling-3-flash)

Ling 3 Flash is currently planned as a 124B-parameter Mixture-of-Experts (MoE) model, with approximately 5.1B parameters activated per token. The model is designed with token efficiency and production-scale agentic inference as key priorities, enabling developers to complete more useful work within constrained token, latency, and serving-cost budgets.

## Ling 3 Flash API Features

- **On-demand Deployment**: On-demand deployments allow you to use Ling 3 Flash on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. · [Docs](https://docs.fireworks.ai/guides/ondemand-deployments)

## Metadata

- **State**: Ready
- **Created on**: 5 AUG, 2026
- **Kind**: Base model
- **Provider**: Fireworks
- **Huggingface**: [inclusionAI/Ling-3.0-flash](https://huggingface.co/inclusionAI/Ling-3.0-flash)

## Specifications

- **Calibrated**: No
- **Mixture-of-Experts**: Yes
- **Parameters**: 127B

## Supporting Functionality

- **Fine-tuning**: Not Supported
- **Serverless**: Not Supported
- **Context Length**: 256k tokens
- **Function Calling**: Supported
- **Embeddings**: Not Supported
- **Rerankers**: Not Supported
- **Supporting image input**: Not Supported
