Kimi K3 on Fireworks: Frontier Intelligence You Can Own

Model Library/Thinking Machines Lab/Inkling Small

Inkling Small

Ready
Deploy on Demand
model path:accounts/fireworks/models/inkling-small

A general-purpose multimodal model that accepts text, image, and audio inputs and generates text outputs.

Inkling Small API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Inkling Small on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
7/31/2026
Kind
Base model
Provider
Thinking Machines Lab
Hugging Face
thinkingmachines/Inkling-Small-NVFP4

Specification

Calibrated
No
Mixture-of-Experts
Yes
Parameters
156B

Supported Functionality

Fine-tuning
Not supported
Serverless
Not supported
Context Length
1040k tokens
Function Calling
Not supported
Embeddings
Not supported
Rerankers
Not supported
Support image input
Supported