Qwen3.5-4B-MLX-4bit
from Qwen/Qwen3.5-4B
Params
4.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-03-02
Apple silicon
Apple MLX models
5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.
Alert me about new Apple/MLX models
8 builds · clear filters
Qwen3.5-4B-OptiQ-4bit
from Qwen/Qwen3.5-4B
Params
4.2B
Weights
≈ 2.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-10-30
Qwen3.5-4B-MLX-8bit
from Qwen/Qwen3.5-4B
Params
4.5B
Weights
≈ 5.1 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-03-02
Qwen3.5-4B-MTP-4bit
from Qwen/Qwen3.5-4B
Params
121M
Weights
≈ 68 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-06-01
Ternary-Bonsai-2-4B-2bit
from Qwen/Qwen3.5-4B
Params
4.5B
Weights
≈ 2.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-10-15
Qwen3.5-4B-MTP-5bit
from Qwen/Qwen3.5-4B
Params
121M
Weights
≈ 83 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-06-01
Qwen3.5-4B-MLX-bf16
from Qwen/Qwen3.5-4B
Params
4.5B
Weights
≈ 9.1 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-02
Qwen3.5-4B-MTP-bf16
from Qwen/Qwen3.5-4B
Params
121M
Weights
≈ 241 MB
Mac memory
8 GB+
apache-2.0 · updated 2026-06-01