Sign InOpen Brain
GitHubGitHub RepoNeeds Review

cactus-compute/needle

Needle 3 runs tool calling, typed extraction, and embeddings locally in an 8–29 MB binary, giving agent builders an offline option for constrained devices.

GitHub · Trending today
Open Source Open MarkdownOpen JSON
Source Summary

Needle 3 packages tool calling, schema-constrained extraction, and text embeddings into a **2-bit, 8–29 MB binary**. Its 121M-parameter ladder supports deployable subnetworks from **2 to 20 layers**, with prebuilt engines under 1 MB.

Practical Implication

For device-side agents, test whether its exact tool selection, typed outputs, and confidence score can replace a network round trip. Fine-tune a smaller subnetwork around a narrow tool set, and use the supplied runtime or C API for deployment.

Agent-Ready Context
Needle 3 packages tool calling, schema-constrained extraction, and text embeddings into a **2-bit, 8–29 MB binary**. Its 121M-parameter ladder supports deployable subnetworks from **2 to 20 layers**, with prebuilt engines under 1 MB.

For device-side agents, test whether its exact tool selection, typed outputs, and confidence score can replace a network round trip. Fine-tune a smaller subnetwork around a narrow tool set, and use the supplied runtime or C API for deployment.

The model deliberately trades away general chat ability, while the published task results use exact-match accuracy and field micro-F1. Local training exports at **4 bits**; the shipped 2-bit quantization uses Cactus infrastructure, and binary telemetry is on by default unless disabled.
Connected Context · Feed7 Judgment

Needle turns the edge-model argument into a deployable specialist: tool choice, typed extraction, and embeddings can fit in megabytes when general conversation is deliberately excluded. It reinforces fine-tuning tiny models for narrow device functions, while its confidence output overlaps Jev’s typed control-flow role. The remaining decision is operational: validate exact-task accuracy and quantization behavior before replacing a network call.

Why Large? Tiny LMs & Agents on Edge/Robotics — Cormac Brick, GoogleNeedle is a concrete implementation of the candidate’s recommendation to fine-tune tiny models for narrow edge functions where memory, reach, and latency dominate.Jev is the fastest-adopted model in AI Gateway historyBoth specialize in typed agent decisions rather than general chat, but Needle targets local deployment and also covers extraction and embeddings.jingyaogong/minimindMiniMind supplies an inspectable small-model training stack, while Needle supplies a much narrower deployment target whose subnetworks can be fine-tuned around a limited tool set.Program-as-Weights: A Programming Paradigm for Fuzzy FunctionsBoth replace large prompted models with compact task specialists, reinforcing the pattern while using different specialization mechanisms: deployable subnetworks versus adapters for a frozen interpreter.
Context Map
modelcoding#open-models#tool-use
Uncertainty
The model deliberately trades away general chat ability, while the published task results use exact-match accuracy and field micro-F1. Local training exports at **4 bits**; the shipped 2-bit quantization uses Cactus infrastructure, and binary telemetry is on by default unless disabled.