03 Categories & Licenses14 VERIFIED ENGINES

Best AI Agents, Tool-Calling LLMs & Self-Hosted Automation Flows (2026)

Orchestrate multi-step autonomous workflows with local tool-calling LLMs (Llama 3.3 70B, Mistral Small 3 24B), self-hosted node pipelines (n8n), and app builders (Bolt.new).

CATEGORYAgents & Orchestration

FASTEST 16GB AGENTMistral Small 3 (24B)

WORKFLOW ENGINEn8n Self-Hosted + AI

SIBLING HUB URLS:/hubs/categories-licenses /category/coding-ides /category/image-design /category/video-cinema /category/voice-audio /category/research /category/agents /category/writing-copy /category/productivity-tools /category/3d-spatial /license/apache-2

Verified Engines for /category/agents

14 RESULTSClick any model card to open its dedicated /ai/[slug] page.

●LOCAL • 95/100

Llama 3.2 3B Instruct

Meta

Ultra-compact 3B open-weight model engineered for on-device summarization, instruction following, and local agent tasks on phones and 4GB laptops.

BASE ARCHITECTURE / Llama-3.2-3B-Instruct

SRuns well (95/100) • Q2_K (~220 tok/s • 22GB free)

ℹTHE BRUTAL TRUTH

The best lightweight model in existence for laptops with integrated graphics. At 2.3GB VRAM it runs on practically any machine at 70+ tok/s for zero dollars.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Extract all action items, assignees, and deadlines from this meeting transcript into JSON.

PREVIEW NOTE

Valid JSON schema with cleanly parsed tasks and dates.

950

Hugging Face↗

●LOCAL • 94/100

Qwen2.5-72B-Instruct

Alibaba / Qwen

Alibaba's 72B general-purpose open-weight titan with 128K context. Ranked top 3 globally across all open foundation models with Apache 2.0 licensing.

BASE ARCHITECTURE / Qwen2.5-72B-Instruct

FToo heavy (13/100) • Needs 42GB at Q4_K_M

Rent a Cloud GPU•$0.14/hr›

ℹTHE BRUTAL TRUTH

The most powerful general-purpose Apache 2.0 model on earth. If you have 48GB VRAM or a 64GB Mac, it out-reasons Llama 3.3 without legal strings.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Analyze the geopolitical implications of rare earth mineral export restrictions on semiconductor supply chains.

PREVIEW NOTE

A multi-dimensional economic and diplomatic analysis examining processing bottlenecks and alternative refining technologies.

920

Hugging Face↗

●CLOUD • 91/100

Zapier AI Agents

Zapier

Autonomous AI agents connected to 7,000+ business applications. Automates customer support triage, CRM lead qualification, and cross-app workflows with natural language rules.

BASE ARCHITECTURE / Zapier Central Agentic Orchestrator

SInstant Cloud Web Studio (0 GB VRAM • Free tier · $19.99/mo)

ℹTHE BRUTAL TRUTH

The simplest way for a business to deploy AI agents that actually take actions across multiple web tools. If you don't want to self-host n8n, this is the answer.

No cardAPI

ILLUSTRATIVE PROMPT

When a customer submits a high-value support ticket in Zendesk, summarize the issue in Slack and draft a personalized response in Gmail.

PREVIEW NOTE

Autonomous agent execution monitoring incoming Zendesk webhooks and triggering Slack alerts.

890

Launch↗

●LOCAL • 91/100

Hermes 3 (Llama 3.1 70B)

Nous Research

Flagship 70B agentic foundation model by Nous Research. Excels at long-form agent execution, complex JSON schemas, and nuanced judgment with 128K context.

BASE ARCHITECTURE / Hermes-3-Llama-3.1-70B

FToo heavy (13/100) • Needs 40GB at Q4_K_M

Rent a Cloud GPU•$0.14/hr›

ℹTHE BRUTAL TRUTH

If you have a 48GB workstation or 64GB Mac, this is the most capable, least constrained 70B model you can run for autonomous workflows.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Draft a comprehensive RFC for a distributed event bus with idempotent consumer guarantees.

PREVIEW NOTE

A formal 5-section RFC complete with architecture diagrams, failure modes, and message delivery contracts.

830

Hugging Face↗

●LOCAL • 87/100

Llama 3.3 70B Instruct

Meta

Meta's reliable 70B dense model for serious reasoning, long-form work, and agentic pipelines that need dependable instruction following.

BASE ARCHITECTURE / Llama 3.3 70B Instruct

FToo heavy (13/100) • Needs 40GB at Q4_K_M

Rent a Cloud GPU•$0.14/hr›

ℹTHE BRUTAL TRUTH

70B capability at 40GB VRAM cost — only worth it if you already own two 24GB cards or a 48GB workstation. Skip on single-GPU rigs.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Design a multi-step research workflow with verification checkpoints.

PREVIEW NOTE

Illustrative agent workflow prompt; not executed here.

803

Hugging Face↗

●LOCAL • 87/100

Hermes 3 (Llama 3.1 8B)

Nous Research

State-of-the-art generalist instruction and roleplay model by Nous Research. Superb function calling, code generation, and multi-turn planning.

BASE ARCHITECTURE / Hermes-3-Llama-3.1-8B

SRuns well (98/100) • Q4_K_M (~141 tok/s • 19GB free)

ℹTHE BRUTAL TRUTH

The best community fine-tune of Llama 3.1 8B. Highly steerable, great at structured tool calling, and free of annoying canned refusals.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Plan a 5-step automated penetration test checklist for an OAuth 2.0 authorization code flow with PKCE.

PREVIEW NOTE

A tactical security audit checklist testing token leakage, replay attacks, and state CSRF validation.

760

Hugging Face↗

●CLOUD • 89/100

Bolt.new

StackBlitz

A browser-based environment for prompting, building, and iterating on full-stack web applications without local setup.

BASE ARCHITECTURE / Model/provider may vary

SInstant Cloud Web Studio (0 GB VRAM • Free / paid usage)

ℹTHE BRUTAL TRUTH

Great demo, real prototype — but production code from Bolt still needs serious cleanup. Use Cursor or Claude for anything you'll maintain.

ILLUSTRATIVE PROMPT

Build a responsive pricing page with accessible form validation.

PREVIEW NOTE

Illustrative task description; no project is generated here.

744

Launch↗

●LOCAL • 88/100

Mistral-Nemo-12B-Instruct

Mistral AI & NVIDIA

Co-developed by Mistral and NVIDIA, this 12B model features Tekken tokenization, a 128K context window, and full Apache 2.0 licensing, fitting easily in 8GB–12GB VRAM.

BASE ARCHITECTURE / Mistral-Nemo-Instruct-2407 (12B)

SRuns well (92/100) • Q4_K_M (~88 tok/s • 16GB free)

ℹTHE BRUTAL TRUTH

The best 12B model in existence. Tekken tokenizer encodes multilingual text with 30% fewer tokens, and it carries true Apache 2.0.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Act as a customer support triage agent: categorize this dispute, identify billing errors, and propose an adjustment.

PREVIEW NOTE

A structured agent evaluation with triage severity, account calculation checks, and credit adjustments.

740

Hugging Face↗

●LOCAL • 89/100

Ministral-8B-Instruct

Mistral AI

Mistral's edge-computing champion with a 128K context window and interleaved sliding window attention, designed for sub-second agentic decision loops.

BASE ARCHITECTURE / Ministral-8B-Instruct-2410

SRuns well (98/100) • Q4_K_M (~141 tok/s • 19GB free)

ℹTHE BRUTAL TRUTH

Phenomenal edge latency and tool calling accuracy, but restricted by Mistral's research license for production commercial SaaS.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Decide whether to execute tool get_weather or search_flights based on query: 'Flight to Boston tomorrow morning'.

PREVIEW NOTE

A structured tool-call payload targeting search_flights with destination 'BOS' and departure date.

705

Hugging Face↗

●SELF • 83/100

n8n + AI

n8n

Workflow automation with AI integrations, a large node library, and self-hosting options for teams that need control over deployment.

BASE ARCHITECTURE / Bring-your-own model

SRuns well (98/100) • Q4_K_M (~176 tok/s • 20GB free)

ℹTHE BRUTAL TRUTH

The only mature self-hostable automation platform with AI. Sustainable-use license is awkward for SaaS resale, but fine for internal workflows.

No cardLocalAPI

ILLUSTRATIVE PROMPT

When a new lead arrives, enrich the record and notify the team.

PREVIEW NOTE

Illustrative automation concept; credentials are not connected.

702

Launch↗

●LOCAL • 86/100

Mistral Small 3

Mistral AI

A 24B Apache-2.0 model tuned for speed and local agentic loops, fitting in 16 GB at 4-bit for real-time workflows.

BASE ARCHITECTURE / Mistral Small 3 (24B)

ARuns well (78/100) • Q4_K_M (~47 tok/s • 9GB free)

ℹTHE BRUTAL TRUTH

The only sub-16GB model on this list that runs real-time agent loops. Trade: weaker reasoning than 27B+ models.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

When a new lead arrives, enrich the record and route it to the right owner.

PREVIEW NOTE

Illustrative automation prompt; credentials are not connected.

699

Hugging Face↗

●LOCAL • 99/100

Liquid LFM3 1.7B

Liquid AI

Liquid AI's Liquid Foundation Model (LFM3) built from first principles with gated convolutions and dynamical systems. Delivers frontier-grade tool calling and agent reasoning with a 256K context at minimal memory footprint.

BASE ARCHITECTURE / LFM3-1.7B (Liquid Dynamical Architecture)

SRuns well (94/100) • Q4_K_M (~220 tok/s • 22GB free)

ℹTHE BRUTAL TRUTH

The most promising post-transformer architecture on the market. If you are building local agent loops that call tools continuously, LFM3 gives you 120+ tokens/sec on almost no VRAM with a 256K context.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Coordinate a 3-agent research synthesis with structured tool schema execution.

PREVIEW NOTE

Accurate function calling payload with verified parameter validation.

680

Hugging Face↗

●LOCAL • 87/100

Command R (35B)

Cohere

Cohere's dedicated 35B open-weight model engineered specifically for retrieval-augmented generation (RAG) and grounded enterprise tool calling across 128K context.

BASE ARCHITECTURE / Command-R-v01 (35B)

BRuns well (61/100) • Q4_K_M (~35 tok/s • 4GB free)

ℹTHE BRUTAL TRUTH

The citation format is brilliant for enterprise document QA, but CC-BY-NC licensing means you cannot commercialize it without Cohere's commercial agreement.

No cardLocalAPIOpen weightsHF

ILLUSTRATIVE PROMPT

Extract claims from this legal deposition, cite line numbers, and flag contradictions.

PREVIEW NOTE

A structured claims matrix with verifiable inline source bracket citations.

640

Hugging Face↗

●LOCAL • 86/100

InternLM2.5-20B-Chat

Shanghai AI Lab

A 20B parameter model featuring an astounding 1-million-token native context window. Designed for book-length document reasoning and complex agent tools.

BASE ARCHITECTURE / InternLM2.5-20B-Chat

ARuns well (77/100) • Q4_K_M (~54 tok/s • 11GB free)

ℹTHE BRUTAL TRUTH

The only sub-24GB model with a verified 1M context window that doesn't hallucinate past 64K. Watch your KV-cache memory at full lengths.

No cardLocalAPIOpen weightsHFPermissive

ILLUSTRATIVE PROMPT

Search a 500-page codebase transcript for all references to deprecated API route /v1/auth/legacy.

PREVIEW NOTE

A structured cross-reference table indexing timestamps, filenames, and replacement routes.

620

Hugging Face↗

Frequently Asked Questions · /category/agents

What is the best local LLM for JSON tool-calling and agent loops?

Mistral Small 3 (24B) for 16GB GPUs and Llama 3.3 70B Instruct for 48GB+ rigs provide the highest schema compliance.

Can n8n connect to local Ollama models?

Yes — self-hosted n8n connects directly to local Ollama or vLLM endpoints for 100% private workflow automation.