Models in Apple’s Core AI catalogue. Apple publishes export recipes in apple/coreai-models that convert each one to run on-device.
Qwen3.5-27B
Downloads, 30 days
1.2K
Memory needed (est.)
20 GB
Quantisation
4-bit, MXFP8
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 4 Mar 2026
whisper-large-v3
Downloads, 30 days
1.1K
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
apache-2.0Added 14 Dec 2025
SmolLM2-360M-Instruct
Downloads, 30 days
869
Memory needed (est.)
3 GB
Quantisation
6-bit, bf16
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 31 Oct 2024
gemma-3n-E4B
Downloads, 30 days
749
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
gemmaAdded 26 Jun 2025
Qwen3.5-35B-A3B
Downloads, 30 days
649
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 3 Mar 2026
sam3
Downloads, 30 days
584
Memory needed (est.)
3 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
otherAdded 24 Dec 2025
gemma-3-4b-it
Downloads, 30 days
297
Memory needed (est.)
5 GB
Quantisation
3-bit, 4-bit DWQ, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 15 Apr 2025
SmolLM2-1.7B-Instruct
Downloads, 30 days
197
Memory needed (est.)
6 GB
Quantisation
4-bit, None
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 31 Oct 2024
Mistral-7B-Instruct-v0.3
Downloads, 30 days
91
Memory needed (est.)
7 GB
Quantisation
4-bit
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 8 Jun 2026
gemma-3-12b-it
Downloads, 30 days
90
Memory needed (est.)
11 GB
Quantisation
4-bit DWQ
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 14 May 2025
OLMo-2-0425-1B-Instruct
Context
4K tokens
Memory needed (est.)
3 GB
Quantisation
4-bit, None
Devices
Runs on: Mac, iPhone
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 11 Sept 2026
edsr-x2
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Jun 2026
efficient-sam-vitt
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Jun 2026
pvt-v2-b0
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Jun 2026
roberta-base
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Jun 2026
wav2vec2-base
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Jun 2026
da3-small
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 8 Jun 2026
Sana_Sprint_0.6B_1024px_diffusers
Builds
—
Memory needed (est.)
—
Quantisation
T8-bit-te4-bit-asym
Devices
Devices not stated
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 25 Sept 2026
Sana_Sprint_1.6B_1024px_diffusers
Builds
—
Memory needed (est.)
—
Quantisation
T8-bit-te4-bit-asym
Devices
Devices not stated
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 3 Nov 2026
t5-base
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 8 Jun 2026
t5-large
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 8 Jun 2026
t5-small
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 8 Jun 2026
gemma-3n-E2B
Context
32K tokens
Memory needed (est.)
6 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 3 Sept 2026
yolos-base
Builds
—
Memory needed (est.)
—
Quantisation
—
Devices
Runs on: Mac, iPhone
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 8 Jun 2026
Load more models Showing 48 of 57 · Previous page