Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.
MiniMax-M2.1
Downloads, 30 days
1.4K
Memory needed (est.)
114 GB
Quantisation
3-bit, 4-bit, MXFP4 +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
modified-mitAdded 26 Dec 2025
VibeVoice-ASR
Downloads, 30 days
1.4K
Memory needed (est.)
9 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 23 Jan 2026
SenseVoiceSmall
Downloads, 30 days
1.4K
Memory needed (est.)
4 GB
Quantisation
—
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
model-licenseAdded 12 Mar 2026
gemma-3n-E2B-it
Downloads, 30 days
1.4K
Memory needed (est.)
7 GB
Quantisation
3-bit, 4-bit, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 26 Jun 2025
Nemotron-Cascade-2-30B-A3B
Downloads, 30 days
1.4K
Memory needed (est.)
22 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
nvidia-open-model-licenseAdded 20 Mar 2026
gemma-4-26B-A4B-it-OptiQ-4bit
Downloads, 30 days
1.4K
Memory needed (est.)
12 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Aug 2026
Unlimited-OCR
Downloads, 30 days
1.4K
Memory needed (est.)
5 GB
Quantisation
4-bit, 6-bit, 8-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 28 Jul 2026
Qwen2-VL-7B-Instruct
Downloads, 30 days
1.4K
Memory needed (est.)
8 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
Qwen2.5-72B-Instruct
Downloads, 30 days
1.4K
Memory needed (est.)
38 GB
Quantisation
3-bit, 4-bit, 6-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
qwenAdded 18 Sept 2024
Josiefied-Qwen3-14B-abliterated-v3
Downloads, 30 days
1.4K
Memory needed (est.)
12 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 4 Jun 2025
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Downloads, 30 days
1.4K
Memory needed (est.)
24 GB
Quantisation
4-bit, MXFP4, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
nvidia-open-model-agreementAdded 28 Apr 2026
MiniCPM5-1B-Claude-Opus-Fable5-V2-Thinking
Downloads, 30 days
1.4K
Memory needed (est.)
3 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Jul 2026
Qwen2.5-Coder-32B-Instruct-abliterated
Downloads, 30 days
1.4K
Memory needed (est.)
19 GB
Quantisation
3-bit, 4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 6 Jan 2025
DeepSeek-Coder-V2-Lite-Instruct
Downloads, 30 days
1.4K
Memory needed (est.)
12 GB
Quantisation
4-bit, 6-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
deepseek-licenseAdded 25 Feb 2025
Huihui-Qwen3.5-4B-Claude-4.6-Opus-abliterated
Downloads, 30 days
1.4K
Memory needed (est.)
6 GB
Quantisation
4-bit, 6-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 17 Mar 2026
Kimi-VL-A3B-Thinking
Downloads, 30 days
1.4K
Memory needed (est.)
—
Quantisation
4-bit, 6-bit, 8-bit
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
qwenAdded 12 Apr 2025
Soprano-1.1-80M
Downloads, 30 days
1.3K
Memory needed (est.)
3 GB
Quantisation
5-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 3 Feb 2026
gemma-4-26B-A4B-it-qat-assistant
Downloads, 30 days
1.3K
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
gemmaAdded 5 Jun 2026
Sage-A1.5
Downloads, 30 days
1.3K
Memory needed (est.)
25 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 22 Oct 2026
flux-3-image-klein-pup
Downloads, 30 days
1.3K
Memory needed (est.)
9 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 18 Oct 2026
gemma-3-27b-it
Downloads, 30 days
1.3K
Memory needed (est.)
—
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
gemmaAdded 12 Mar 2025
gemma-4-31b
Downloads, 30 days
1.3K
Memory needed (est.)
23 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
translategemma-27b-it
Downloads, 30 days
1.3K
Memory needed (est.)
19 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 15 Jan 2026
Mellum2.1-12B-A2.5B-Thinking
Downloads, 30 days
1.3K
Memory needed (est.)
14 GB
Quantisation
6-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 11 Oct 2026
Load more models Showing 336 of 2,334 · Previous page