Models in Apple’s Core AI catalogue. Apple publishes export recipes in apple/coreai-models that convert each one to run on-device.
gpt-oss-20b
Downloads, 30 days
178K
Memory needed (est.)
16 GB
Quantisation
4-bit, MXFP4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 29 Aug 2025
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
Qwen3.5-4B
Downloads, 30 days
111K
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Mar 2026
Qwen3-0.6B
Downloads, 30 days
91K
Memory needed (est.)
3 GB
Quantisation
3-bit, 4-bit, 4-bit DWQ +3
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Apr 2025
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
Qwen3-8B
Downloads, 30 days
36K
Memory needed (est.)
7 GB
Quantisation
3-bit, 4-bit, 4-bit DWQ +3
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Apr 2025
Qwen3.5-9B
Downloads, 30 days
36K
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Mar 2026
Qwen3-4B
Downloads, 30 days
32K
Memory needed (est.)
4 GB
Quantisation
3-bit, 4-bit, 4-bit DWQ +3
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Apr 2025
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-Coder-30B-A3B-Instruct
Downloads, 30 days
27K
Memory needed (est.)
17 GB
Quantisation
3-bit, 4-bit, 4-bit DWQ +6
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 31 Jul 2025
Qwen3-1.7B
Downloads, 30 days
19K
Memory needed (est.)
3 GB
Quantisation
3-bit, 4-bit, 4-bit DWQ +5
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Apr 2025
FLUX.2-klein-4B
Downloads, 30 days
18K
Memory needed (est.)
5 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 23 May 2026
Muse-Glimmer-30B
Downloads, 30 days
17K
Memory needed (est.)
24 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 10 Aug 2026
whisper-large-v3-turbo
Downloads, 30 days
16K
Memory needed (est.)
3 GB
Quantisation
4-bit, 8-bit, fp16
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
mitAdded 14 Dec 2025
Qwen3.5-2B
Downloads, 30 days
14K
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 2 Mar 2026
embeddinggemma-2
Downloads, 30 days
14K
Memory needed (est.)
4 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 6 Oct 2026
Qwen3.5-0.8B
Downloads, 30 days
7.6K
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 2 Mar 2026
Phi-4-mini-instruct
Downloads, 30 days
4.8K
Memory needed (est.)
5 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 27 Feb 2025
SmolLM2-135M-Instruct
Downloads, 30 days
4.0K
Memory needed (est.)
3 GB
Quantisation
None
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 31 Oct 2024
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
gemma-3n-E4B-it
Downloads, 30 days
1.6K
Memory needed (est.)
7 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
Qwen3.5-122B-A10B
Downloads, 30 days
1.5K
Memory needed (est.)
46 GB
Quantisation
2-bit, MXFP4, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Apr 2026
Load more models Showing 24 of 57