Pluto-AI-Labs/Apollo-VL-Edge-3B-MLX-4bit

Apollo-VL-Edge-3B (MLX 4bit)

Intelligence isn't about scale. It's about precision.

---

Overview

Apollo-VL-Edge-3B (MLX 4bit) is the native Apple Silicon port of Apollo-VL-Edge-3B, engineered by Pluto AI Labs. This repository contains the MLX 4bit quantization, converted from the original FP16 Transformers checkpoint and optimized to run natively on Apple M-Series chips (M1/M2/M3/M4) using the unified memory architecture via the mlx-vlm framework.

This is the most compact MLX variant — designed for maximum memory efficiency on entry-level Apple Silicon hardware while retaining strong visual reasoning capability.

---

Specifications

Property	Value
Base Model	Pluto-AI-Labs/Apollo-VL-Edge-3B
Architecture	Qwen2.5-VL
Format	MLX 4bit
File Size	~2.9 GB
Recommended RAM	8 GB (M-Series Mac)
Target Hardware	Apple M1/M2/M3/M4 (8GB+)
Precision Loss	Moderate

---

Quick Start

Install the mlx-vlm framework and run inference locally:

```bash pip install mlx-vlm ```

```bash python -m mlx_vlm.generate
--model Pluto-AI-Labs/Apollo-VL-Edge-3B-MLX-4bit
--image ./your_image.png
--prompt "Analyze this image step-by-step."
--max-tokens 512 ```

Python API

```python from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config

model_path = "Pluto-AI-Labs/Apollo-VL-Edge-3B-MLX-4bit"

model, processor = load(model_path) config = load_config(model_path)

prompt = apply_chat_template( processor, config, "Analyze this image step-by-step.", num_images=1 )

output = generate( model, processor, "./your_image.png", prompt, max_tokens=512, verbose=True ) ```

---

MLX Quantization Family

All Apollo-VL MLX variants are available for different hardware targets:

Variant	File Size	Recommended RAM	Precision Loss
MLX FP16	~7.5 GB	16 GB	Baseline
MLX 8bit	~4.3 GB	8 GB	Minimal
MLX 6bit	~3.6 GB	8 GB	Low
MLX 4bit (This Repo)	~2.9 GB	8 GB	Moderate

💡 For the original FP16 Transformers checkpoint, GGUF quantizations, and full benchmark results, see the main model repository.

---

About Pluto AI Labs

Pluto AI Labs is an independent open-source AI research lab focused on efficient intelligence, multimodal reasoning, model distillation, and edge deployment. We explore how capable AI systems can be made smaller, faster, and more accessible without requiring hyperscale infrastructure.

• GitHub: https://github.com/Pluto-AI-Labss
• Hugging Face: https://huggingface.co/Pluto-AI-Labs

---

Citation

If you use Apollo-VL-Edge-3B in your research or projects, please cite:

```bibtex @misc{apollo_vl_edge_3b, title = {Apollo-VL-Edge-3B: Elite Visual Reasoning on Edge Hardware}, author = {Siddharth N.R. and Pluto AI Labs}, year = {2026}, howpublished = {Hugging Face}, url = {https://huggingface.co/Pluto-AI-Labs/Apollo-VL-Edge-3B} } ```

---

Apollo-VL-Edge-3B · MLX 4bit

Precision over scale. Reasoning at the edge.

Built by Pluto AI Labs