MXFP8 Open on Hugging Face
Parameters
4.0B
Weights (est.)
≈ 4.3 GB
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/Qwen3-4B-Base (finetune)
- Vendor
- Qwen
- Task
- Embeddings
- Quantisation
- MXFP8
- Licence
- apache-2.0
- Downloads
- 854 in the last 30 days · 12K all time · 2 likes
- Published
- 2026-02-11 · updated 2026-02-11 (9mo ago)
- Tags
- sentence-transformers, qwen3, text-generation, sentence-similarity, text-embeddings-inference
Other MLX builds of Qwen/Qwen3-4B-Base
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| Qwen3-Embedding-4B-mxfp8 (this one) | MXFP8 | ≈ 4.3 GB | 8 GB+ | 854 |
| Qwen3-Reranker-4B-mxfp8 | MXFP8 | ≈ 4.3 GB | 8 GB+ | 887 |