Pairing Claude Code with Local Models

Ollama, LM Studio, and llama.cpp now support native Anthropic Messages API connections, enabling Claude Code to run entirely on local models for code completion, refactoring, and debugging tasks. By setting environment variables like `ANTHROPIC_BASE_URL` and model tier mappings, developers can redirect Claude Code's API calls to local inference servers, eliminating per-token costs and rate limits. The setup requires at least 16 GB RAM and Ollama v0.14.0 or later for Anthropic API compatibility.

Pairing Claude Code with Local Models Local models in 2026 are good enough. For the tasks Claude Code handles daily: code completion, refactoring, debugging, codebase explanation; a well-chosen quantized model running locally covers the vast majority of real use cases at zero per-token cost and with no rate limits. Introduction Agentic coding sessions are expensive. A single Claude Code session — reading files, writing code, running tests, iterating — can burn 10–50x more tokens than a plain chat conversation. At scale, that adds up fast. Add rate limits that can interrupt a long-running workflow mid-session, and the dependency on a third-party API that can change pricing, enforce stricter policies, or go down at any point, and the case for local inference becomes straightforward. Local models in 2026 are good enough. For the tasks Claude Code handles daily — code completion, refactoring, debugging, codebase explanation — a well-chosen quantized model running locally covers the vast majority of real use cases at zero per-token cost and with no rate limits. This article covers three inference backends Ollama , , and LM Studio https://lmstudio.ai/ , the exact environment variables and configuration files to wire each one to Claude Code, a curated table of models worth running, and the troubleshooting fixes for the issues you will actually hit. llama.cpp https://github.com/ggml-org/llama.cpp How Claude Code Connects to Any Local Model The mechanism is simpler than most guides make it look. Claude Code sends requests in the Anthropic Messages API format. By default those requests go to Anthropic's servers. Setting ANTHROPIC BASE URL redirects them to any server that speaks the same format, which now includes Ollama, LM Studio, and llama.cpp natively. According to the official Claude Code environment variables documentation, the variables that matter for this setup are: ANTHROPIC BASE URL : redirects all API calls from Anthropic's servers to whatever URL you set. Set this to your local inference server address. ANTHROPIC API KEY : the API key sent in the request header. Local servers typically ignore authentication, so this is usually set to a placeholder string like " local " or " ollama ." ANTHROPIC AUTH TOKEN : an alternative auth header. Some local servers check for this instead of the API key. Set it to the same placeholder. ANTHROPIC DEFAULT SONNET MODEL , ANTHROPIC DEFAULT HAIKU MODEL , and ANTHROPIC DEFAULT OPUS MODEL : Claude Code internally requests different model tiers depending on the task. These three variables map each tier to your local model's name. Without them, Claude Code sends requests for claude-sonnet-4-20250514 to your local server, which will reject the request because no such model exists locally. In January 2026, Ollama added native support for the Anthropic Messages API, which was the technical change that made this workflow practical without translation proxies. LM Studio added a native /v1/messages endpoint in version 0.4.1. llama.cpp has had direct Anthropic API support for longer. All three now speak Claude Code's native protocol. A clean architecture diagram showing Claude Code, Ollama, LM Studio, and llama.cpp | Image by Author Backend 1: Ollama Ollama is the right starting point. It handles all the complexity of model management — downloading weights, quantization, GPU and CPU allocation, and serving — behind a simple command-line interface CLI . One command to install, one command to pull a model, a few environment variables to configure. It runs as a background service after install, so there is no manual server start required. Prerequisites - macOS, Linux, or Windows WSL2 recommended on Windows - At least 16 GB RAM for practical use 32 GB recommended - GPU with 8+ GB VRAM for GPU inference, or CPU-only with enough RAM - Ollama v0.14.0 or later required for Anthropic Messages API support Install Ollama: macOS and Linux -- one command install curl -fsSL https://ollama.com/install.sh | sh Verify the version -- must be 0.14.0+ for Claude Code compatibility ollama version Expected: ollama version is 0.14.x or higher Windows: download the installer from https://ollama.com Native Windows support has improved significantly in recent releases After installation, Ollama starts automatically as a background service on port 11434 . You can verify it is running: Check the Ollama server is live curl http://localhost:11434 Expected response: Ollama is running Pull a coding model: GLM-4.7-Flash -- recommended starting point Strong tool calling, 128K context, fits on 8 GB VRAM Apache 2.0 license ollama pull glm-4.7-flash:latest Qwen3-Coder -- strong code generation and instruction following Requires 20+ GB VRAM for the full model ollama pull qwen3-coder Devstral-Small -- specifically designed for agentic coding workflows Community-tested for Claude Code compatibility 24B, requires 16+ GB VRAM ollama pull devstral-small-2:24b Verify the model is downloaded and ready ollama list Shows all pulled models with their sizes and modification dates // Configuring Claude Code to Use Ollama Option 1: Shell export current terminal session only Redirect Claude Code to your local Ollama server export ANTHROPIC BASE URL="http://localhost:11434" Local servers do not require real authentication Set these to any non-empty string -- Ollama ignores the value export ANTHROPIC API KEY="ollama" export ANTHROPIC AUTH TOKEN="ollama" Map Claude Code's model tier requests to your local model name Claude Code internally requests sonnet/haiku/opus -- these variables translate those tier names to whatever model you have pulled locally export ANTHROPIC DEFAULT SONNET MODEL="glm-4.7-flash:latest" export ANTHROPIC DEFAULT HAIKU MODEL="glm-4.7-flash:latest" export ANTHROPIC DEFAULT OPUS MODEL="glm-4.7-flash:latest" Launch Claude Code -- it will now use Ollama instead of the Anthropic API claude Option 2: ~/.claude/settings.json permanent, applies to all sessions This approach survives terminal restarts and applies every time you launch Claude Code. Claude Code reads environment variables from settings.json at startup so they take effect no matter how claude was launched. Create or edit ~/.claude/settings.json : { "env": { "ANTHROPIC BASE URL": "http://localhost:11434", "ANTHROPIC API KEY": "ollama", "ANTHROPIC AUTH TOKEN": "ollama", "ANTHROPIC DEFAULT SONNET MODEL": "glm-4.7-flash:latest", "ANTHROPIC DEFAULT HAIKU MODEL": "glm-4.7-flash:latest", "ANTHROPIC DEFAULT OPUS MODEL": "glm-4.7-flash:latest" } } Option 3: .env file in project directory per-project override If you want a specific project to use a different model while keeping your global settings on the Anthropic API: .env in your project root -- loaded automatically by Claude Code ANTHROPIC BASE URL=http://localhost:11434 ANTHROPIC API KEY=ollama ANTHROPIC AUTH TOKEN=ollama ANTHROPIC DEFAULT SONNET MODEL=qwen3-coder ANTHROPIC DEFAULT HAIKU MODEL=qwen3-coder ANTHROPIC DEFAULT OPUS MODEL=qwen3-coder Verify the connection: Launch Claude Code with a simple test claude Inside Claude Code, run a basic prompt: What model are you running? A local model should respond without making any Anthropic API calls. To confirm no external calls are being made, run with verbose logging: claude --verbose Look for lines showing requests going to localhost:11434 rather than api.anthropic.com Full working sequence from scratch: curl -fsSL https://ollama.com/install.sh | sh 1. Install Ollama ollama pull glm-4.7-flash:latest 2. Pull model ~4 GB export ANTHROPIC BASE URL="http://localhost:11434" 3. Redirect Claude Code export ANTHROPIC API KEY="ollama" 4. Set placeholder auth export ANTHROPIC AUTH TOKEN="ollama" export ANTHROPIC DEFAULT SONNET MODEL="glm-4.7-flash:latest" export ANTHROPIC DEFAULT HAIKU MODEL="glm-4.7-flash:latest" export ANTHROPIC DEFAULT OPUS MODEL="glm-4.7-flash:latest" claude 5. Launch Backend 2: LM Studio LM Studio is the right choice if you want a graphical interface for browsing and managing models rather than working entirely in the terminal. Since version 0.4.1, it includes a native Anthropic-compatible /v1/messages endpoint — the same path Claude Code expects — so no translation layer or proxy is needed. Prerequisites: - macOS, Windows, or Linux - GPU with 6+ GB VRAM recommended CPU-only is possible but slow - Download from lmstudio.ai or use the CLI installer for headless servers Install and configure LM Studio: On a server or VM without a GUI -- CLI installer curl -fsSL https://releases.lmstudio.ai/cli/install.sh | bash Or download the desktop app from https://lmstudio.ai for GUI use GUI setup steps: - Open LM Studio and search for a coding model search "qwen coder" or "devstral" . - Download the model. LM Studio handles quantization selection automatically. - Go to the Local Server tab the < icon in the left sidebar . - Set the context size. LM Studio recommends starting with at least 25,000 tokens and increasing for better results. - Click Start Server . - Note the port default: 1234 and copy the model name exactly as shown. Note: Copy the model identifier exactly. LM Studio displays the exact string you need to pass to ANTHROPIC DEFAULT SONNET MODEL . A mismatch here is the most common failure mode. Configure Claude Code: Set the base URL to LM Studio's local server export ANTHROPIC BASE URL="http://localhost:1234" export ANTHROPIC API KEY="lm-studio" export ANTHROPIC AUTH TOKEN="lm-studio" Replace the model name with what LM Studio shows for your loaded model Copy it exactly -- including any version suffix or quantization tag export ANTHROPIC DEFAULT SONNET MODEL="qwen2.5-coder-32b-instruct" export ANTHROPIC DEFAULT HAIKU MODEL="qwen2.5-coder-32b-instruct" export ANTHROPIC DEFAULT OPUS MODEL="qwen2.5-coder-32b-instruct" Or persistently in ~/.claude/settings.json : { "env": { "ANTHROPIC BASE URL": "http://localhost:1234", "ANTHROPIC API KEY": "lm-studio", "ANTHROPIC AUTH TOKEN": "lm-studio", "ANTHROPIC DEFAULT SONNET MODEL": "qwen2.5-coder-32b-instruct", "ANTHROPIC DEFAULT HAIKU MODEL": "qwen2.5-coder-32b-instruct", "ANTHROPIC DEFAULT OPUS MODEL": "qwen2.5-coder-32b-instruct" } } How to run: 1. Start the LM Studio server from the GUI Local Server tab Start Server 2. Set environment variables export ANTHROPIC BASE URL="http://localhost:1234" export ANTHROPIC API KEY="lm-studio" export ANTHROPIC AUTH TOKEN="lm-studio" export ANTHROPIC DEFAULT SONNET MODEL="your-model-name-here" export ANTHROPIC DEFAULT HAIKU MODEL="your-model-name-here" export ANTHROPIC DEFAULT OPUS MODEL="your-model-name-here" 3. Launch claude Backend 3: llama.cpp llama.cpp is the right choice when you need direct control over inference parameters — quantization type, KV cache configuration, batch size, thread count — or when you are running on a server and want the lowest overhead. It has native Anthropic Messages API support, so no proxy or translation layer is needed. Prerequisites: - A GGUF-format model file download from Hugging Face; search for "GGUF" versions of any model - CUDA-capable GPU for GPU inference, or CPU-only for slower inference - CMake and a C++ compiler for source builds on Linux/CUDA, source is recommended Install llama.cpp: macOS -- Homebrew is simplest brew install llama.cpp Linux with CUDA -- build from source for best GPU performance git clone https://github.com/ggml-org/llama.cpp cd llama.cpp cmake -B build -DGGML CUDA=ON Enable CUDA acceleration cmake --build build --config Release Build Binaries in ./build/bin/ Linux CPU-only build cmake -B build cmake --build build --config Release Windows -- pre-built binaries available at: https://github.com/ggml-org/llama.cpp/releases Download the CUDA or CPU variant matching your hardware Download a GGUF model: Install the Hugging Face CLI if you do not have it pip install huggingface-hub Download GLM-4.7-Flash in Q4 K XL quantization ~4.5 GB This quantization offers a good size/quality balance for coding huggingface-cli download unsloth/GLM-4.7-Flash-GGUF \ GLM-4.7-Flash-UD-Q4 K XL.gguf \ --local-dir ./models/ Or download Qwen3-Coder in Q4 quantization ~15 GB for 32B huggingface-cli download Qwen/Qwen3-Coder-32B-Instruct-GGUF \ qwen3-coder-32b-instruct-q4 k m.gguf \ --local-dir ./models/ Start the llama.cpp server: Start llama-server with Anthropic API support and a 128K context window llama-server \ --model ./models/GLM-4.7-Flash-UD-Q4 K XL.gguf \ --alias "glm-4.7-flash" \ This name goes in ANTHROPIC DEFAULT SONNET MODEL --port 8001 \ --ctx-size 131072 \ 128K context -- important for large codebases --flash-attn \ Memory-efficient attention, improves speed --n-gpu-layers 99 Offload all layers to GPU; remove for CPU-only For CPU-only inference no GPU : llama-server \ --model ./models/GLM-4.7-Flash-UD-Q4 K XL.gguf \ --alias "glm-4.7-flash" \ --port 8001 \ --ctx-size 32768 \ Reduce context size on CPU to keep memory manageable --threads 8 Match your CPU core count Key flags explained: --alias : the model name string Claude Code will send in requests. Set ANTHROPIC DEFAULT SONNET MODEL to match this exactly. --ctx-size : context window in tokens. 131072 = 128K . Larger is better for codebase analysis but uses more VRAM. Reduce if you get out-of-memory errors. --flash-attn : Flash Attention reduces peak VRAM by processing attention in smaller blocks. Enable it whenever your build supports it. --n-gpu-layers 99 : offloads all transformer layers to the GPU. The server automatically uses fewer layers if VRAM is tight. Configure Claude Code: export ANTHROPIC BASE URL="http://localhost:8001" export ANTHROPIC API KEY="llama-cpp" export ANTHROPIC AUTH TOKEN="llama-cpp" Must match the --alias you passed to llama-server exactly export ANTHROPIC DEFAULT SONNET MODEL="glm-4.7-flash" export ANTHROPIC DEFAULT HAIKU MODEL="glm-4.7-flash" export ANTHROPIC DEFAULT OPUS MODEL="glm-4.7-flash" How to run: Terminal 1: start the llama.cpp server llama-server \ --model ./models/GLM-4.7-Flash-UD-Q4 K XL.gguf \ --alias "glm-4.7-flash" \ --port 8001 \ --ctx-size 131072 \ --flash-attn \ --n-gpu-layers 99 Terminal 2: configure and launch Claude Code export ANTHROPIC BASE URL="http://localhost:8001" export ANTHROPIC API KEY="llama-cpp" export ANTHROPIC AUTH TOKEN="llama-cpp" export ANTHROPIC DEFAULT SONNET MODEL="glm-4.7-flash" export ANTHROPIC DEFAULT HAIKU MODEL="glm-4.7-flash" export ANTHROPIC DEFAULT OPUS MODEL="glm-4.7-flash" claude The Complete settings.json Environment variable exports last only as long as the terminal session. For a durable configuration, use ~/.claude/settings.json . Claude Code reads variables from this file at startup so they apply no matter how Claude was launched — from the terminal, from a VS Code task, or from a script. Here is a production-ready settings.json with all variables explained: { "env": { "ANTHROPIC BASE URL": "http://localhost:11434", "ANTHROPIC API KEY": "ollama", "ANTHROPIC AUTH TOKEN": "ollama", "ANTHROPIC DEFAULT SONNET MODEL": "glm-4.7-flash:latest", "ANTHROPIC DEFAULT HAIKU MODEL": "glm-4.7-flash:latest", "ANTHROPIC DEFAULT OPUS MODEL": "glm-4.7-flash:latest", "CLAUDE CODE DISABLE EXPERIMENTAL BETAS": "1" } } Why CLAUDE CODE DISABLE EXPERIMENTAL BETAS: "1" matters: When using Claude Code through non-Anthropic backends, Claude Code adds Anthropic-specific experimental beta flags to request headers — flags that third-party and local servers do not recognize. This causes Error: Unexpected value s for the anthropic-beta header on most local inference servers. Setting this variable to "1" strips those headers before the request goes out, which eliminates the error without affecting any core Claude Code functionality. Switching between backends: If you work with multiple backends — Ollama for daily use, the Anthropic API for complex tasks — the cleanest approach is maintaining separate shell scripts rather than editing settings.json back and forth: use-local.sh -- switch to Ollama export ANTHROPIC BASE URL="http://localhost:11434" export ANTHROPIC API KEY="ollama" export ANTHROPIC AUTH TOKEN="ollama" export ANTHROPIC DEFAULT SONNET MODEL="glm-4.7-flash:latest" export ANTHROPIC DEFAULT HAIKU MODEL="glm-4.7-flash:latest" export ANTHROPIC DEFAULT OPUS MODEL="glm-4.7-flash:latest" echo "Claude Code → local Ollama glm-4.7-flash " use-anthropic.sh -- switch back to the Anthropic API unset ANTHROPIC BASE URL unset ANTHROPIC AUTH TOKEN unset ANTHROPIC DEFAULT SONNET MODEL unset ANTHROPIC DEFAULT HAIKU MODEL unset ANTHROPIC DEFAULT OPUS MODEL ANTHROPIC API KEY should already be set to your real key in your rc file echo "Claude Code → Anthropic API" Source either script in your current session: source ./use-local.sh claude When you need the real API for a complex task: source ./use-anthropic.sh claude Best Local Models for Claude Code in 2026 Hardware is the main constraint. For Claude Code with local models to be genuinely usable for coding tasks rather than just a demo, aim for 32 GB of RAM — Apple Silicon unified memory or PC RAM. 16 GB is viable with smaller quantized models and CPU offload, but generation speed will be noticeably slower on multi-step agentic tasks. Model | VRAM Needed | Context | Strengths | License | Pull Command | |---|---|---|---|---|---| | ollama pull glm-4.7-flash devstral-small-2:24b https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512 ollama pull devstral-small-2:24b qwen3-coder https://huggingface.co/collections/Qwen/qwen3-coder ollama pull qwen3-coder qwen3.5:27b https://huggingface.co/Qwen/Qwen3.5-27B ollama pull qwen3.5:27b gemma4:26b https://huggingface.co/google/gemma-4-26B-A4B ollama pull gemma4:26b Troubleshooting Common Issues Connection refused when launching Claude Code: The inference server is not running. This is the most common issue and the easiest to diagnose. Check if Ollama is running curl http://localhost:11434 Expected: "Ollama is running" Check if LM Studio server is running curl http://localhost:1234/v1/models Should return a JSON list of loaded models Check if llama-server is running curl http://localhost:8001/health Should return {"status":"ok"} If not running -- start the server first, then launch Claude Code ollama serve Ollama LM Studio: use the GUI Local Server tab llama.cpp: run the llama-server command from the Backend 3 section Model not found or unknown model error: The model name in your ANTHROPIC DEFAULT SONNET MODEL does not match what the server knows. List all models Ollama has available ollama list The model name in ANTHROPIC DEFAULT SONNET MODEL must match EXACTLY including the tag -- "glm-4.7-flash:latest" not "glm-4.7-flash" Verify with a direct API call to confirm what the server sees curl http://localhost:11434/v1/models Tool calls failing or returning errors: For streaming tool calls, which Claude Code uses when executing functions or scripts, Ollama version 0.14.3-rc1 or later is required. Earlier versions in the 0.14.x series had incomplete streaming tool call support. Check your Ollama version ollama version If below 0.14.3, update Ollama curl -fsSL https://ollama.com/install.sh | sh anthropic-beta header error:You will see: Error: Unexpected value s for the anthropic-beta header . This happens because Claude Code adds Anthropic-specific experimental beta flags that local servers do not recognize. Fix it by adding this to your settings.json env block: "CLAUDE CODE DISABLE EXPERIMENTAL BETAS": "1" Reverting to the Anthropic API: Shell session -- unset the redirect variables unset ANTHROPIC BASE URL unset ANTHROPIC AUTH TOKEN unset ANTHROPIC DEFAULT SONNET MODEL unset ANTHROPIC DEFAULT HAIKU MODEL unset ANTHROPIC DEFAULT OPUS MODEL Then make sure your real API key is set echo $ANTHROPIC API KEY Should show your sk-ant-... key, not a placeholder If you used settings.json -- remove or comment out the env block and restart Claude Code Slow generation speed: For agentic Claude Code tasks, generation speed matters because each tool call is a round trip. If speed is inadequate:- Switch to a smaller or more aggressively quantized model Q4 K M instead of Q8 . - Enable --flash-attn in llama.cpp if not already set. - Reduce context size --ctx-size ; larger contexts are slower to prefill. - On Ollama, set OLLAMA NUM GPU LAYERS=99 in your environment to force maximum GPU offload. Conclusion What used to require fragile adapters and hacks is now a five-step process. Install the inference backend, pull a model, set three environment variables, and Claude Code routes to your local machine instead of Anthropic's API. The configuration takes under five minutes once you have the model downloaded. The practical result is a coding assistant that costs nothing to run after setup, has no rate limits, keeps your code entirely on your machine, and covers the vast majority of real coding use cases at quality levels that were not available in local models a year ago. Start with Ollama and glm-4.7-flash — it has the lowest hardware requirement, the most consistent tool-calling support, and the fastest path to a working setup. Once that is running, scale up the model based on your hardware and the quality level you actually need. is a software engineer and technical writer passionate about leveraging cutting-edge technologies to craft compelling narratives, with a keen eye for detail and a knack for simplifying complex concepts. You can also find Shittu on Shittu Olumide https://www.linkedin.com/in/olumide-shittu/