Best Local LLMs for OpenClaw
Self-hosted agentic assistant with first-class Ollama support
OpenClaw is a self-hosted, model-agnostic agentic assistant that runs across your messaging apps and executes tools (browser, cron, canvas, skills) on your own hardware. It supports local open-weight models through a native Ollama provider, where the agent loop depends entirely on the model emitting structured tool calls. Pick a model trained for that, and connect through the right endpoint.
Best pick
Qwen3.6 35B-A3B
Newest Qwen3 MoE; the Qwen3 line has the most stable tool calling and rarely drops params.
What OpenClaw needs
Reliable structured tool-calling at 64K+ context (Ollama's own integration docs recommend at least 64K tokens for local models), accessed via the native Ollama API. Not the /v1 OpenAI-compatible endpoint, which OpenClaw's docs warn breaks tool calls.
OpenClaw Local LLM Tier List
Newest Qwen3 MoE; the Qwen3 line has the most stable tool calling and rarely drops params.
Same proven Qwen3 tool-calling reliability; the family featured in OpenClaw config recipes.
Gemma 4 ships native function calling; OpenClaw docs treat gemma4 as the local default.
Native function calling in an efficient MoE; a top consumer-hardware agent pick.
Explicitly named in OpenClaw Ollama recipes; dense Qwen3 tool reliability.
Solid tool calling and large context; named in OpenClaw recipes.
Directly featured in OpenClaw docs (qwen3.5:9b, num_ctx 32768).
Qwen3-Coder 30B is RL-trained for multi-step agentic loops; strong but prior-gen.
Mistral supports tools; mid reliability with decent context.
Reasoning-strong starter, but less battle-tested for sustained tool loops.
Great code completion, but not RL-trained for OpenClaw-style multi-step tool loops.
Small, older Llama tool-calling; prone to malformed calls.
Predates native function calling; poor agentic fit.
Tiers weigh tool-calling reliability, context window, and coding quality for OpenClaw specifically. A model can rank higher for one tool than another. RAM figures are for Q4 quantization. Sources are listed below.
Local setup notes
Pull a model with Ollama and OpenClaw auto-discovers it. Point it at the native API base URL (http://host:11434, no /v1) and set num_ctx to 64K+, the minimum Ollama's own integration docs recommend for local models. Quality and tool-call reliability scale with model size, so prefer the largest variant your hardware allows.
OpenClaw official site ↗The weekly local-AI refresh
New open-weight models, real Apple Silicon benchmarks, and the one model worth running on your Mac this week. Free, one email a week, unsubscribe anytime.
By subscribing you agree to our Privacy Policy and to receive the weekly email. Unsubscribe anytime.
Frequently Asked Questions
Can I run OpenClaw fully local with no API costs?+
Why does the endpoint URL matter so much for OpenClaw?+
Why are the Qwen2.5-Coder models only mid-tier here despite being great coders?+
Sources
- OpenClaw: self-hosted, model-agnostic agentic assistant ↗
- OpenClaw Ollama provider: /v1 endpoint breaks tool calling, use the native URL ↗
- OpenClaw local-model guidance: prefer the largest variant you can host ↗
- Ollama integration docs: recommend at least 64K context for local models ↗
- Qwen3 most stable tool calling; Gemma 4 native function calling ↗
Other AI Coding Tools
Claude Code
Anthropic's terminal coding agent, driven by a local model
OpenCode
Open-source terminal coding agent (Ollama / OpenAI-compatible)
Aider
Terminal AI pair-programmer with its own edit-format leaderboard
Cline
Autonomous coding agent for VS Code (formerly Claude Dev)
Roo Code
Autonomous VS Code agent with modes (a Cline fork)
Continue.dev
Open-source chat, edit & autocomplete for VS Code / JetBrains
Goose
Block's open-source autonomous developer agent (MCP-driven)
Open Claude Code
Open-source Claude Code CLI reimplementation, with an undocumented endpoint override for local models
Codex
OpenAI's coding agent, driven by a local model via its built-in Ollama provider