---
license: apache-2.0
base_model: Qwen/Qwen3-8B
library_name: basert
pipeline_tag: text-generation
tags:
  - basert
  - apple-silicon
  - quantized
---

# Qwen3-8B

[BaseRT](https://github.com/basecompute/baseRT) `.base` builds of
[`Qwen/Qwen3-8B`](https://huggingface.co/Qwen/Qwen3-8B) for fast local inference on Apple
Silicon (Metal).

## Files

| File | Precision | Size |
|------|-----------|------|
| `Qwen3-8B-Q4.base` | 4-bit | 4.3G |
| `Qwen3-8B-Q8.base` | 8-bit | 7.9G |

## Usage

```bash
curl -LsSf https://basecompute.co/install.sh | sh
basert pull basecompute/Qwen3-8B
basert chat basecompute/Qwen3-8B
```

Released under the apache-2.0 license, inherited from the base model.