Hugging Face's logo

nisavid
/
MemReranker-4B-OptiQ-4bit

Text Generation
MLX
Safetensors
sentence-transformers
English
Chinese
qwen3
reranker
memory
agent
cross-encoder
conversational
4-bit precision
Model card Files
xet
 Community

Built with mlx-optiq, the MLX-native toolkit to quantize, fine-tune, and serve LLMs locally on Apple Silicon (no PyTorch, no cloud). Try the Lab 路 All OptiQ quants 路 Docs

Downloads last month
13
Safetensors
Model size
4B params
Tensor type
U32
路
BF16
路
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for nisavid/MemReranker-4B-OptiQ-4bit

Base model

Qwen/Qwen3-4B-Base
Finetuned
Qwen/Qwen3-Reranker-4B
Finetuned
IAAR-Shanghai/MemReranker-4B
Quantized
(1)
this model