Instructions to use eunjay/WebSailor-3B-MLX-8bit-community with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eunjay/WebSailor-3B-MLX-8bit-community with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("eunjay/WebSailor-3B-MLX-8bit-community")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use eunjay/WebSailor-3B-MLX-8bit-community with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "eunjay/WebSailor-3B-MLX-8bit-community"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "eunjay/WebSailor-3B-MLX-8bit-community"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use eunjay/WebSailor-3B-MLX-8bit-community with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "eunjay/WebSailor-3B-MLX-8bit-community"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default eunjay/WebSailor-3B-MLX-8bit-community

Run Hermes

hermes

OpenClaw new

How to use eunjay/WebSailor-3B-MLX-8bit-community with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "eunjay/WebSailor-3B-MLX-8bit-community"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "eunjay/WebSailor-3B-MLX-8bit-community" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MLX LM

How to use eunjay/WebSailor-3B-MLX-8bit-community with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "eunjay/WebSailor-3B-MLX-8bit-community"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "eunjay/WebSailor-3B-MLX-8bit-community"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "eunjay/WebSailor-3B-MLX-8bit-community",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

WebSailor-3B-MLX-8bit-community / README.md

eunjay

docs: clarify MLX usage and tool-call validation

e4b7fec verified 1 day ago

preview code

Raw

History Blame Contribute Delete

3.45 kB

metadata

license: apache-2.0
language: en
library_name: mlx
base_model: Alibaba-NLP/WebSailor-3B
base_model_revision: b317a15261674d83d851f0a14761840583bb9dce
tags:
  - mlx
  - mlx-lm
  - 8-bit
  - web-agent
  - web-search
pipeline_tag: text-generation

WebSailor-3B-MLX-8bit-community

Unofficial community MLX conversion of Alibaba-NLP/WebSailor-3B for Apple Silicon.

This repository is not an official Alibaba-NLP or Hugging Face release and does not imply endorsement by the original authors.

Conversion details

Source model: Alibaba-NLP/WebSailor-3B
Source revision: b317a15261674d83d851f0a14761840583bb9dce
Output format: MLX Safetensors
Quantization: 8-bit affine, group size 64
Effective quantization reported by mlx-lm: 8.501 bits/weight
Conversion tool: mlx-lm 0.31.2 with mlx 0.31.1
Original license: Apache-2.0; see LICENSE

Install MLX-LM with:

pip install -U mlx-lm

The conversion command was:

HF_HUB_DISABLE_XET=1 mlx_lm.convert \
  --hf-path Alibaba-NLP/WebSailor-3B \
  --mlx-path ./WebSailor-3B-MLX-8bit \
  --quantize \
  --q-bits 8 \
  --q-group-size 64

Local usage

MLX-LM can resolve the Hugging Face repository ID directly:

pip install -U mlx-lm

mlx_lm.generate \
  --model eunjay/WebSailor-3B-MLX-8bit-community \
  --prompt "Reply with one short sentence." \
  --max-tokens 64

For a local checkout, replace the repository ID with ./WebSailor-3B-MLX-8bit.

The model weights alone do not browse the web; web-search or browser tool calls require an external tool/backend and an agent loop.

Tool calling and web-search scope

The original WebSailor-3B agent harness uses both search and visit tools through WebAgent. This MLX conversion was validated only with a one-shot search tool-call smoke test; the full WebSailor/WebAgent search + visit harness was not run against this conversion.

For the smoke test, an explicit JSON-format instruction was supplied so the model emitted a parser-compatible call:

If you need the search tool, output exactly one valid JSON object between <tool_call> and </tool_call>. Use double-quoted keys and this shape: {"name":"search","arguments":{"query":["query text"]}}. Never output YAML labels such as name: or arguments:.

The local OpenAI-compatible MLX server parsed that single call successfully. The search service itself remains external and must execute the requested query. This result is not validation of the complete WebSailor search agent or its visit flow.

Compatibility note

Hugging Face may display Pi, Hermes, or OpenClaw connection examples automatically for compatible serving endpoints. Those examples indicate endpoint connectivity, not validation of WebSailor's search-agent behavior. Tool-call markers and parsers can vary across MLX-LM versions, so treat the result above as a one-shot smoke test and verify the full agent harness before production use.

Attribution

Please retain the original model attribution and Apache-2.0 license when redistributing this conversion. This repository contains converted weights and supporting tokenizer/configuration files; it is not a replacement for the original model card or project code.