Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.
MiniCPM5-1B
Downloads, 30 days
3.2K
Memory needed (est.)
3 GB
Quantisation
4-bit, 6-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 26 May 2026
NVIDIA-Nemotron-3.5-Bolt-E4B-OptiQ
Downloads, 30 days
3.2K
Memory needed (est.)
8 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
openmdw-1.1Added 24 Oct 2026
DeepSeek-V4-Pro-Qwen3.5-9B
Downloads, 30 days
3.2K
Memory needed (est.)
9 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 7 Aug 2026
Meta-Llama-3-8B-Instruct
Downloads, 30 days
3.1K
Memory needed (est.)
8 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3Added 18 Apr 2024
gemma-4-12B-it
Downloads, 30 days
3.0K
Memory needed (est.)
10 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 5 Jun 2026
chatterbox-turbo-fp16
Downloads, 30 days
3.0K
Memory needed (est.)
6 GB
Quantisation
fp16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 17 Dec 2025
Dolphin3.0-Llama3.2-3B
Downloads, 30 days
2.9K
Memory needed (est.)
5 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3.2Added 22 Jan 2025
MiMo-V2.6-Distill-Qwen-9B
Downloads, 30 days
2.9K
Memory needed (est.)
8 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 21 Sept 2026
gemma-2-2b-it
Downloads, 30 days
2.9K
Memory needed (est.)
4 GB
Quantisation
4-bit, 8-bit, fp16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 31 Jul 2024
Qwen2.5-Coder-0.5B-Instruct
Downloads, 30 days
2.9K
Memory needed (est.)
3 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 11 Nov 2024
LFM2.5-2.6B
Downloads, 30 days
2.9K
Memory needed (est.)
4 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
lfm1.0Added 4 Aug 2026
embeddinggemma-300m
Downloads, 30 days
2.9K
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 4 Sept 2025
gemma-3n-E2B-it
Downloads, 30 days
2.7K
Memory needed (est.)
5 GB
Quantisation
4-bit, 4-bit DWQ, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 29 Jun 2025
translategemma-12b-it
Downloads, 30 days
2.7K
Memory needed (est.)
10 GB
Quantisation
4-bit, 6-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 15 Jan 2026
csm-1b
Downloads, 30 days
2.7K
Memory needed (est.)
4 GB
Quantisation
8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 6 May 2025
phi-4
Downloads, 30 days
2.7K
Memory needed (est.)
8 GB
Quantisation
2-bit, 3-bit, 4-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 16 Dec 2024
Voxtral-Mini-4B-Realtime-2602
Downloads, 30 days
2.7K
Memory needed (est.)
6 GB
Quantisation
4-bit, fp16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 6 Feb 2026
Llama-3.2-3B-Instruct-uncensored
Downloads, 30 days
2.7K
Memory needed (est.)
5 GB
Quantisation
6-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 23 Apr 2025
gemma-3-270m-it
Downloads, 30 days
2.7K
Memory needed (est.)
3 GB
Quantisation
4-bit, 4-bit DWQ, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 9 Aug 2025
GLM-OCR
Downloads, 30 days
2.6K
Memory needed (est.)
5 GB
Quantisation
bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 3 Feb 2026
Qwen3-Embedding-8B
Downloads, 30 days
2.6K
Memory needed (est.)
7 GB
Quantisation
4-bit DWQ
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 8 Jun 2025
Qwen2.5-Coder-7B
Downloads, 30 days
2.5K
Memory needed (est.)
7 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 Sept 2024
Qwen2.5-Coder-14B-Instruct-abliterated
Downloads, 30 days
2.5K
Memory needed (est.)
12 GB
Quantisation
4-bit, 6-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 22 Feb 2025
GLM-OCR
Downloads, 30 days
2.5K
Memory needed (est.)
4 GB
Quantisation
4-bit, 5-bit, 6-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 3 Feb 2026
Load more models Showing 144 of 1,412 · Previous page