Ling-3.0-tiny
Ling-3.0-tiny is available now for rag, agents, and long context with open-source and 131k context; evaluate it while provider pricing coverage matures.
InclusionAI is Ant Group's artificial general intelligence research lab, responsible for developing the Ling series of l
No tracked provider token pricing is available yet.
About
inclusionAI Ling-3.0-tiny is a lightweight hybrid-reasoning MoE in the Ling 3.0 series with 7.9B total and 1.3B active parameters. It stacks Kimi Delta Attention and Multi-Head Latent Attention 3:1 and routes 8 of 128 experts plus 1 shared expert. It is validated for local deployment on NVIDIA DGX Spark and Apple Silicon. Config max_position_embeddings is 131,072. MIT License, with base and GGUF variants.
Provider price ladder
No tracked provider token pricing is available for this model yet.
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
inclusionAI/Ling-3.0-tinyInclusionAI is Ant Group's artificial general intelligence research lab, responsible for developing the Ling series of l
No tracked provider token pricing is available yet.