Unsloth-DeepSeek-R1-Distill-Qwen-32B-4bit
from unsloth/DeepSeek-R1-Distill-Qwen-32B
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-02-26
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
7 builds · clear filters
Qwen3-14B-4bit-AWQ
from unsloth/Qwen3-14B
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-08-29
Llama-3_3-Nemotron-Super-49B-v1_5-mlx-4Bit
from unsloth/Llama-3_3-Nemotron-Super-49B-v1_5
Params
50B
Weights
≈ 28.1 GB
Mac memory
48 GB+
nvidia-open-model-license · updated 2025-09-15
Unsloth-DeepSeek-R1-Distill-Qwen-14B-4bit
from unsloth/DeepSeek-R1-Distill-Qwen-14B
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-02-26
Unsloth-Phi-4-4bit
from unsloth/phi-4
Params
15B
Weights
≈ 8.2 GB
Mac memory
16 GB+
mit · updated 2025-01-13
Unsloth-Phi-4-mini-instruct-4bit
from unsloth/Phi-4-mini-instruct
Params
3.8B
Weights
≈ 2.2 GB
Mac memory
8 GB+
mit · updated 2025-05-29
JOSIEv4o-8b-stage1-beta-4bit
from unsloth/llama-3-8b-bnb-4bit
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+
apache-2.0 · updated 2024-06-24