Needle 3
Needle 3 is available now for agents, classification, and json / tool use with open-source; evaluate it while provider pricing coverage matures.
- Family
- Needle
- Released
- 2026-09-17
- Context
- 8K
- Parameters
- 121M
- Specialization
- on-device
- Openness
- Open source
- License
- Apache 2.0OSI-approvedCommercial use: permitted
- Weights
- Available
- Code
- Unknown
- Training
- Pretrained
Cactus Compute, Inc. builds automation foundation models for tiny devices (mobiles, wearables, smart home, robots, micro
WebsiteNo tracked provider token pricing is available yet.
About
Needle 3 is Cactus Compute's sliceable automation foundation model for tiny devices, announced 2026-09-17 (MCP-verified @cactuscompute tip 2100685924401295764 + first-party /needle). One set of weights; every depth from 2 to 20 layers is its own deployable model (intelligence ladder). Params ~25–121M at CQ2-bit (2L ~25M, 4L ~29M, 8L ~52M, 16L ~98M, 20L ~121M / config total_parameters 121021910); footprint 8–29MB (.cact; full 20L ~29MB). Positioning: does not chat — every turn is tool calling or schema extraction (structured JSON); also returns text embeddings. First-party claims it can match DeepSeek V4 Flash (esp.
Providers
No active provider routes are tracked for this model yet.
Capabilities
Benchmark peer barsfor Agents
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
needle-3needle3Cactus Compute, Inc. builds automation foundation models for tiny devices (mobiles, wearables, smart home, robots, micro
WebsiteNo tracked provider token pricing is available yet.