Instructions to use OsaurusAI/VibeThinker-3B-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OsaurusAI/VibeThinker-3B-MXFP4 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("OsaurusAI/VibeThinker-3B-MXFP4")

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 OsaurusAI/VibeThinker-3B-MXFP4 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/VibeThinker-3B-MXFP4"

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": "OsaurusAI/VibeThinker-3B-MXFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use OsaurusAI/VibeThinker-3B-MXFP4 with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "OsaurusAI/VibeThinker-3B-MXFP4"

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 "OsaurusAI/VibeThinker-3B-MXFP4" \
  --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 OsaurusAI/VibeThinker-3B-MXFP4 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "OsaurusAI/VibeThinker-3B-MXFP4"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "OsaurusAI/VibeThinker-3B-MXFP4"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "OsaurusAI/VibeThinker-3B-MXFP4",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use OsaurusAI/VibeThinker-3B-MXFP4 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 "OsaurusAI/VibeThinker-3B-MXFP4"

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 OsaurusAI/VibeThinker-3B-MXFP4

Run Hermes

hermes

Atomic Chat

VibeThinker-3B · MXFP4

Official OsaurusAI MXFP4 microscaling (4.25 bpw) build of WeiboAI/VibeThinker-3B (MIT) — a 3B dense reasoning model (Qwen2). Quantized by Osaurus; runs on Apple Silicon via Osaurus / mlx_lm. Emits <think> reasoning blocks.

Usage

python -m mlx_lm generate --model OsaurusAI/VibeThinker-3B-MXFP4 --prompt "What is 17 + 28?"

Or load in Osaurus.

Provenance

Base: WeiboAI/VibeThinker-3B © Weibo AI — MIT
Quantization: Osaurus · MXFP4 microscaling (4.25 bpw) · eric@osaurus.ai

Downloads last month: 20

Safetensors

Model size

0.6B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for OsaurusAI/VibeThinker-3B-MXFP4

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-Coder-3B

Finetuned

WeiboAI/VibeThinker-3B

Quantized

(53)

this model