---
title: Apriel-1.5-15b-Thinker-2bit-MLX
canonical_url: "https://www.modelscope.cn/models/mlx-community/Apriel-1.5-15b-Thinker-2bit-MLX"
md_url: "https://www.modelscope.cn/models/mlx-community/Apriel-1.5-15b-Thinker-2bit-MLX.md"
repository: mlx-community/Apriel-1.5-15b-Thinker-2bit-MLX
last_updated: 2026-07-15
license: mit
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - pixtral
architectures:
  - LlavaForConditionalGeneration
base_model:
  - ServiceNow-AI/Apriel-1.5-15b-Thinker
base_model_relation: quantized
parameters: 1.8B
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 150
stars: 0
tags:
  - mlx
  - apple-silicon
  - multimodal
  - vision-language
  - pixtral
  - llava
  - quantized
  - 2bit
---

# Apriel-1.5-15b-Thinker-2bit-MLX

> Apriel-1.5-15b-Thinker-2bit-MLX - mlx-community 在 ModelScope 开源的模型。Apriel-1.5-15B-Thinker — MLX 2-bit (Apple Silicon)

mlx-community/Apriel-1.5-15b-Thinker-2bit-MLX 是 ModelScope 魔搭社区上的 1.8B 参数image-text-to-text模型，采用 mit 许可，基于 ServiceNow-AI/Apriel-1.5-15b-Thinker 构建。

- **Repository**: mlx-community/Apriel-1.5-15b-Thinker-2bit-MLX
- **License**: mit
- **Tasks**: image-text-to-text
- **Parameters**: 1.8B
- **Base model**: ServiceNow-AI/Apriel-1.5-15b-Thinker
- **Tags**: mlx, apple-silicon, multimodal, vision-language, pixtral, llava, quantized, 2bit
- **Downloads**: 150
- **Stars**: 0
- **Last updated**: 2026-07-15

Source: https://www.modelscope.cn/models/mlx-community/Apriel-1.5-15b-Thinker-2bit-MLX

---

# Apriel-1.5-15B-Thinker — **MLX 2-bit** (Apple Silicon)

**Format:** MLX (Mac, Apple Silicon)  
**Quantization:** 2-bit (ultra-compact)  
**Base:** ServiceNow-AI/Apriel-1.5-15B-Thinker  
**Architecture:** Pixtral-style LLaVA (vision encoder → 2-layer projector → decoder)

This repository provides a **2-bit MLX** build of Apriel-1.5-15B-Thinker for **tight-memory** Apple-Silicon devices. It prioritizes **small footprint and fast load** over absolute accuracy. If quality is your primary concern, prefer the **6-bit** MLX variant.

---

## 🔎 What is Apriel-1.5-15B-Thinker?

Apriel-1.5-15B-Thinker is an open multimodal **reasoning** model that scales a Pixtral-style VLM with **depth upscaling**, two-stage **multimodal continual pretraining (CPT)**, and high-quality **SFT with explicit reasoning traces** (math, coding, science, tool-use). The training recipe focuses on **mid-training** (no RLHF/RM), delivering strong image-grounded reasoning at modest compute.

> This card documents the **2-bit MLX** conversion. Expect **higher compression** and **noticeable quality drop** vs FP/Int or 6-bit, especially on fine-grained text in images, dense charts, or long-chain reasoning.

---

## 📦 What’s in this repo

- `config.json` (MLX config mapped for Pixtral-style VLM)  
- `mlx_model*.safetensors` (2-bit quantized shards)  
- `tokenizer.json`, `tokenizer_config.json`  
- `processor_config.json` / `image_processor.json`  
- `model_index.json` and metadata

---

## ✅ Intended uses

- On-device **image understanding** where memory is constrained (light captioning, object/layout descriptions)  
- Quick triage of **screenshots, UI mocks, simple charts**, forms with broad structure  
- Educational demos of **VLMs on Mac** w/ minimal RAM budget

## ⚠️ Limitations

- 2-bit is **very lossy**. Expect degradation on:
  - OCR-heavy tasks, small fonts, dense tables
  - Multi-step math/coding with visual grounding
  - Long context or many images
- May hallucinate or miss small details. **Human review is required** for critical use.

---

## 🖥️ Apple-Silicon guidance

- **Works:** M1/M2 (8–16 GB) for short prompts + single image; **recommended:** M3/M4 for smoother throughput.  
- Use GPU:
  ```bash
  --device mps