Qwen3-4B-Sky-High-Hermes-bfloat16
from ZeroXClem/Qwen3-4B-Sky-High-Hermes
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-01-19
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
68 builds · page 2 of 2 · clear filters
Qwen3-4B-Thinking-2507-6bit
from Qwen/Qwen3-4B-Thinking-2507
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-08-06
Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v3-bfloat16
from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v3
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2026-03-13
Qwen3-4B-Thinking-2507-gabliterated-6bit
from Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+
updated 2026-01-17
Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4-mxfp4
from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v4
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
updated 2026-03-13
Qwen3-4B-Thinking-2507-gabliterated-bfloat16
from Goekdeniz-Guelmez/Qwen3-4B-Thinking-2507-gabliterated
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+
updated 2026-01-17
Josiefied-Qwen3-4B-Instruct-2507-abliterated-v2-bfloat16
mlx-community/Josiefied-Qwen3-4B-Instruct-2507-abliterated-v2-bfloat16
Params
—
Weights
—
Mac memory
—
updated 2026-03-13
Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v3-8bit
mlx-community/Josiefied-Qwen3-4B-Instruct-2507-gabliterated-v3-8bit
Params
—
Weights
—
Mac memory
—
updated 2026-03-13