Qwen3.5-9B-MLX-4bit
4-bit MLX quantization of Qwen3.5-9B-MLX-4bit
Conversion
Quantized using mlx_lm.convert with 4-bit quantization (q_bits=4, q_group_size=64)
Usage
from mlx_lm import load, generate
model, tokenizer = load("rafal-adamczyk/Qwen3.5-9B-MLX-4bit")
response = generate(model, tokenizer, prompt="Hello!", verbose=True)
Original Model
See Qwen/Qwen3.5-9B for full details.
License
Apache 2.0 (inherited from original)
- Downloads last month
- 173
Model size
1B params
Tensor type
BF16
·
U32 ·
F32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for rafal-adamczyk/Qwen3.5-9B-MLX-4bit
Base model
Qwen/Qwen3.5-9B-Base Finetuned
Qwen/Qwen3.5-9B