You can deploy this model and start earning money today!

rafal-adamczyk/
Qwen3.5-9B-MLX-8bit

Name: Qwen3.5-9B-MLX-8bit
Availability: InStock

Views

No views yet

Qwen3.5-9B-MLX-8bit

4-bit MLX quantization of Qwen3.5-9B-MLX-8bit

Quantized using mlx_lm.convert with 8-bit quantization (q_bits=8, q_group_size=64)

python

from mlx_lm import load, generate

model, tokenizer = load("username/repo_name")
response = generate(model, tokenizer, prompt="Hello!", verbose=True)

See Qwen/Qwen3.5-9B for full details.

Apache 2.0 (inherited from original)