MLX Community · First MLX build 11 Feb 2026
Qwen3-Reranker-8B
MLX
Text apache-2.0
A reranking model, with one MLX build at MXFP8.
- Parameters
- — Not published
- Quantisation
- MXFP8 Qwen3-Reranker-8B-mxfp8
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 226 This build, last 30 days
- Task
- Reranking Text
- MLX builds
- 1 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/Qwen3-Reranker-8B-mxfp8MLX builds
1 on mlx-community| Qwen3-Reranker-8B-mxfp8 | MXFP8 | — | — | 226 |
|---|
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.