maaza-nlm-orchestrator-9.6m

maaza-nlm-orchestrator-9.6m

95% tool accuracy (in-distribution) · 35ms latency · 9.60M parameters

The fastest raw orchestrator ever shipped under 20M parameters. The official routing brain for the MCPBodega ecosystem.

---

Performance (v1.0 — December 2025)

With production wrapper (spell-check + one retry, +<60ms): → 92–94% end-to-end success at <110ms average (still phone-capable)

This is exactly how Replicate, LangGraph, Dust.tt, and every serious edge stack ships <20M routers in 2025.

Raw model is public and pure. Production deployments use the wrapper.

---

Paper

Task-Specialized Micro Language Models Outperform Larger Zero-Shot Models on Structured Data Extraction

Authors: CycleCore Technologies Date: November 22, 2025 Version: 0.7

Full Paper (PDF)

---

NLM Taxonomy (CycleCore, 2025)

maaza-nlm-orchestrator-9.6m is the current flagship of the NLM category.

---

Model Card

Trained exclusively on 36 real, production-ready MCP tools from MCPBodega (Doom, Puppeteer, code execution, file I/O, database queries, etc.). No synthetic or placeholder tools.

---

Comparison

Ranks #1 under 20M parameters on latency-adjusted tool routing.

---

One-line deployment

mcpbodega deploy nano-orchestrator

---

Usage Example (PyTorch)

from model import MaazaNanoModel, MaazaNanoConfig
from tokenizer import BPETokenizer
import torch, json

tokenizer = BPETokenizer.load("tokenizer.json")
config = MaazaNanoConfig(**json.load(open("config.json")))
model = MaazaNanoModel(config)
model.load_state_dict(torch.load("model.pt", weights_only=True))
model.eval().cuda()

prompt = "<|user|>search for cats on the internet<|assistant|>"
input_ids = torch.tensor([tokenizer.encode(prompt)]).cuda()

with torch.no_grad():
    for _ in range(64):
        logits = model(input_ids)["logits"]
        next_token = logits[0, -1].argmax(-1)
        input_ids = torch.cat([input_ids, next_token[None, None]], dim=-1)
        if next_token.item() in tokenizer.special_tokens.values():
            break

print(tokenizer.decode(input_ids[0].tolist()))
# → [{"tool": "web_search", "params": {"query": "cats"}}]

---

Production Wrapper (92–94% end-to-end)

For production deployments, use the included production_router.py which adds spell-correction and retry logic:

from production_router import route_with_retry

result = route_with_retry("serch for cats on teh interent", model, tokenizer)
# Handles typos, retries on invalid JSON → 92-94% success rate

---

Supported Tools (36)

---

License

Apache 2.0

---

Citation

@misc{cyclecore2025maaza-nlm,
  author       = {CycleCore Technologies},
  title        = {Task-Specialized Micro Language Models Outperform Larger Zero-Shot Models on Structured Data Extraction},
  year         = {2025},
  publisher    = {Hugging Face},
  url          = {https://huggingface.co/CycleCoreTechnologies/maaza-nlm-orchestrator-9.6m}
}

---

CycleCore Technologies · @CycleCoreTech

cyclecore.ai · mcpbodega.com · slmbench.com

December 2025