MXFP8 Open on Hugging Face
Parameters
596M
Weights (est.)
≈ 633 MB
Mac memory (est.)
8 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- Qwen/Qwen3-0.6B-Base (finetune)
- Vendor
- Qwen
- Task
- Reranking
- Quantisation
- MXFP8
- Licence
- apache-2.0
- Downloads
- 913 in the last 30 days · 4.8K all time · 2 likes
- Published
- 2026-02-11 · updated 2026-02-11 (9mo ago)
- Tags
- qwen3, text-generation
Other MLX builds of Qwen/Qwen3-0.6B-Base
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-0.6B-Base-4bit | 4-bit | ≈ 335 MB | 8 GB+ | 1.5K |
| Qwen3-Reranker-0.6B-mxfp8 (this one) | MXFP8 | ≈ 633 MB | 8 GB+ | 913 |
| Qwen3-Embedding-0.6B-mxfp8 | MXFP8 | ≈ 633 MB | 8 GB+ | 750 |
| Qwen3-0.6B-Base-8bit | 8-bit | ≈ 633 MB | 8 GB+ | 63 |
| Qwen3-0.6B-Base-bf16 | bf16 | ≈ 1.2 GB | 8 GB+ | 76 |
| Qwen3-0.6B-Base | — | ≈ 1.2 GB | 8 GB+ | 44 |