---
title: Qwen3-VL 8B Apple Silicon Benchmarks
summary: The mid-size Qwen3-VL, 5.8 GB. Slower than E4B on both tests.
---

# Qwen3-VL 8B Apple Silicon Benchmarks

The mid-size Qwen3-VL, 5.8 GB. Slower than E4B on both tests.

- Repo: `mlx-community/Qwen3-VL-8B-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: 5.8 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 | 5.89s | 24.72s |

## Speed

- Still: 5.89s, prefill 2.02s, 179 tokens
- Video chunk: 24.72s, 737 tokens