Views
No views yet
| Property | Value |
|---|---|
| Source | Qwen/Qwen3-1.7B |
| Format | executorch |
| Quantization | int4 weight-only |
| Backend | xnnpack |
| Fusion | disabled |
| Total Size | 2842.7 MB |
| File | Size |
|---|---|
README.md | 0.0 MB |
chat_template.jinja | 0.0 MB |
export_config.json | 0.0 MB |
model.pte | 2831.8 MB |
tokenizer.json | 10.9 MB |
tokenizer_config.json | 0.0 MB |
1val engine = ExecuTorchEngine(modelDir = "/path/to/Qwen3-1.7B-ET")
2engine.prefill(prompt) { token -> print(token) }