---
title: Qwen3-VL 4B Apple Silicon Benchmarks
summary: The smallest Qwen3-VL on the list, 3.1 GB. A little faster than E4B on stills. Slower on chunks, because it writes more tokens.
---

# Qwen3-VL 4B Apple Silicon Benchmarks

The smallest Qwen3-VL on the list, 3.1 GB. A little faster than E4B on stills. Slower on chunks, because it writes more tokens.

- Repo: `mlx-community/Qwen3-VL-4B-Instruct-4bit`
- Maker: Alibaba
- Maker page: /resources/groundslate/benchmarks/makers/alibaba
- Line: Qwen3-VL
- Line page: /resources/groundslate/benchmarks/makers/alibaba/qwen3-vl
- License: [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)

Qwen3-VL is Alibaba's vision-language line. GroundSlate runs the 4-bit MLX conversions from mlx-community.

- Size: 3.1 GB
- Tools: list_models, set_vision_model, index_video, index_image, process_video, reindex_clips, name_video, summarize_video
- Suite: /resources/groundslate/benchmarks/vision

## On each Mac

| Machine | Status | Still | Video chunk |
| --- | --- | --- | --- |
| MacBook Pro, Apple M3 Max, 64 GB unified memory | Reference Mac | 3.12s | 14.14s |

## Speed

- Still: 3.12s, prefill 1.05s, 159 tokens
- Video chunk: 14.14s, 665 tokens