Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.
Qwen3.8-27B
Downloads, 30 days
169K
Memory needed (est.)
3 GB
Quantisation
4-bit, MXFP4, 8-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Aug 2026
Qwen3.5-0.8B
Downloads, 30 days
72K
Memory needed (est.)
3 GB
Quantisation
3-bit, 4-bit, MXFP4 +5
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Mar 2026
Qwen3.6-35B-A3B
Downloads, 30 days
57K
Memory needed (est.)
3 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 16 Apr 2026
Qwen3.6-27B
Downloads, 30 days
55K
Memory needed (est.)
3 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 22 Apr 2026
gemma-3-4b-it-qat
Downloads, 30 days
43K
Memory needed (est.)
6 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
qwenAdded 15 Apr 2025
Qwen3.5-9B
Downloads, 30 days
32K
Memory needed (est.)
9 GB
Quantisation
3-bit, 4-bit, MXFP4 +5
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Mar 2026
gemma-4-E4B-it
Downloads, 30 days
31K
Memory needed (est.)
8 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Apr 2026
gemma-4-E2B-it
Downloads, 30 days
29K
Memory needed (est.)
5 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Apr 2026
Qwen3.5-2B
Downloads, 30 days
25K
Memory needed (est.)
3 GB
Quantisation
3-bit, 4-bit, MXFP4 +5
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Mar 2026
Qwen2.5-VL-7B-Instruct
Downloads, 30 days
24K
Memory needed (est.)
8 GB
Quantisation
3-bit, 4-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 29 Jan 2025
gemma-3-4b-it
Downloads, 30 days
21K
Memory needed (est.)
6 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 12 Mar 2025
Qwen2-VL-2B-Instruct
Downloads, 30 days
20K
Memory needed (est.)
4 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 27 Sept 2024
Qwen3-VL-4B-Instruct
Downloads, 30 days
20K
Memory needed (est.)
5 GB
Quantisation
3-bit, 4-bit, 5-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Oct 2025
gemma-4-E2B-it-qat-mobile
Downloads, 30 days
17K
Memory needed (est.)
5 GB
Quantisation
8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 29 Jul 2026
gemma-4-31B-it
Downloads, 30 days
15K
Memory needed (est.)
10 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Apr 2026
gemma-4-E4B-it-qat-mobile
Downloads, 30 days
13K
Memory needed (est.)
7 GB
Quantisation
8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 11 Aug 2026
gemma-4-12B-it
Downloads, 30 days
13K
Memory needed (est.)
10 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 3 Jun 2026
gemma-4-12B-it-qat
Downloads, 30 days
11K
Memory needed (est.)
10 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 5 Jun 2026
Llama-3.2-11B-Vision-Instruct
Downloads, 30 days
9.0K
Memory needed (est.)
9 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3.2Added 18 Oct 2024
Qwen3-VL-2B-Instruct
Downloads, 30 days
7.7K
Memory needed (est.)
4 GB
Quantisation
3-bit, 4-bit, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 21 Oct 2025
Qwen3-VL-8B-Instruct
Downloads, 30 days
7.6K
Memory needed (est.)
8 GB
Quantisation
3-bit, 4-bit, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Oct 2025
Qwen2.5-VL-3B-Instruct
Downloads, 30 days
7.6K
Memory needed (est.)
5 GB
Quantisation
3-bit, 4-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 29 Jan 2025
llava-v1.6-mistral-7b
Downloads, 30 days
7.1K
Memory needed (est.)
7 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 22 Jun 2024
llava-1.5-7b
Downloads, 30 days
6.8K
Memory needed (est.)
7 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama2Added 23 Apr 2024
Load more models Showing 24 of 225