Model
Model explorer
Ling 3.0 Tiny
CLOSEDinclusionAI · Ling 3.0 family · released Aug 6, 2026
inclusionAI's (Ant Group) lightweight edge-deployment model in the Ling 3.0 series, positioned below Ling-3.0-flash: only 1.3B activated parameters for real-time interaction, lightweight code assistance, local knowledge-base retrieval and tool calling with low latency on constrained hardware. Ant's own docs say it 'will be open-sourced in the near future' as of launch, so it currently ships closed/proprietary; served free of charge (promotional) via OpenRouter at launch with no confirmed first-party metered price, hence price: null here.
ReasoningCodingVisionFunction callingTool useAgentic
—
Elo · unrated
Parameters
7.9B
Active params
1.3B (MoE)
Context
256K tokens
Architecture
Sparse MoE, 7.9B total / 1.3B active parameters, switchable Thinking/Instant reasoning modes, designed for edge and on-device deployment
License
Proprietary (open-source release planned but not yet published)
Languages
—
API price (in/out)
No hosted API
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
—
Output / M tok
—
API price — · each benchmark row carries its own source badge (see methodology)