Skip to content
Apple · on-device

Apple Core AI models

The models Apple supports converting to its Core AI .aimodel format for running on-device: 58 models across 70 export presets, read directly from apple/coreai-models, checked 19m ago. Apple publishes the export recipes there, not the converted models: each entry tells you which model, which platforms, and the settings Apple uses.

Latest repository change 3h ago: Route reasoning to reasoning_content when the chat template opens the think block (#508)

Alert me about new Apple/CoreAI models

Clear filters

Language models 36

gemma-3-4b-it

google/gemma-3-4b-it
macOS
Google · Gemma 1 preset
Family
gemma3
Context
128K
Compression
4bit

gemma-3-12b-it

google/gemma-3-12b-it
macOS
Google · Gemma 1 preset
Family
gemma3
Context
128K
Compression
4bit

gemma-3n-E2B

google/gemma-3n-E2B
macOS
Google · Gemma 1 preset
Family
gemma3n
Context
32K
Compression
4bit

gemma-3n-E2B-it

google/gemma-3n-E2B-it
macOS
Google · Gemma 1 preset
Family
gemma3n
Context
32K
Compression
4bit

gemma-3n-E4B

google/gemma-3n-E4B
macOS
Google · Gemma 1 preset
Family
gemma3n
Context
32K
Compression
4bit

gemma-3n-E4B-it

google/gemma-3n-E4B-it
macOS
Google · Gemma 1 preset
Family
gemma3n
Context
32K
Compression
4bit

gemma-4-E2B-it

google/gemma-4-E2B-it
iOS
Google · Gemma 1 preset
Family
gemma4
Context
128K
Compression
none

gemma-4-E4B-it

google/gemma-4-E4B-it
iOS
Google · Gemma 1 preset
Family
gemma4
Context
128K
Compression
none

gpt-oss-20b

openai/gpt-oss-20b
macOS
OpenAI · gpt-oss 1 preset
Family
gpt-oss
Context
32K
Compression
none

Mistral-7B-Instruct-v0.3

mistralai/Mistral-7B-Instruct-v0.3
macOSiOS
Mistral 2 presets
Family
mistral
Context
8K
Compression
4bit, 4bit_weight_palettized_group8

Mixtral-8x7B-Instruct-v0.1

mistralai/Mixtral-8x7B-Instruct-v0.1
macOS
Mistral 1 preset
Family
mixtral
Context
32K
Compression
4bit

Muse-Glimmer-30B

meta-models/Muse-Glimmer-30B
macOS
meta-models 1 preset
Family
muse_glimmer
Context
128K
Compression
4bit

Muse-Glimmer-30B-assistant

meta-models/Muse-Glimmer-30B-assistant
macOS
meta-models 1 preset
Family
muse_glimmer
Context
128K
Compression
none

OLMo-2-0425-1B-Instruct

allenai/OLMo-2-0425-1B-Instruct
macOSiOS
Ai2 · OLMo 2 presets
Family
olmo2
Context
4K
Compression
4bit, none

Phi-3-mini-4k-instruct

microsoft/Phi-3-mini-4k-instruct
macOS
Microsoft · Phi 1 preset
Family
phi3
Context
4K
Compression
4bit

Phi-3.5-mini-instruct

microsoft/Phi-3.5-mini-instruct
macOS
Microsoft · Phi 1 preset
Family
phi3
Context
128K
Compression
4bit

Phi-4-mini-instruct

microsoft/Phi-4-mini-instruct
macOS
Microsoft · Phi 1 preset
Family
phi3
Context
128K
Compression
4bit

Qwen2.5-1.5B-Instruct

Qwen/Qwen2.5-1.5B-Instruct
macOSiOS
Qwen 3 presets
Family
qwen2.5
Context
32K
Compression
4bit, 4bit_weights_8bit_kv_cache, 4bit_weight_palettized_group8

Qwen3-0.6B

Qwen/Qwen3-0.6B
macOSiOS
Qwen 2 presets
Family
qwen3
Context
8K
Compression
4bit, none

Qwen3-1.7B

Qwen/Qwen3-1.7B
macOSiOS
Qwen 2 presets
Family
qwen3
Context
32K
Compression
4bit, none

Qwen3-4B

Qwen/Qwen3-4B
macOSiOS
Qwen 3 presets
Family
qwen3
Context
40K
Compression
4bit, 4bit_weights_8bit_kv_cache, none

Qwen3-8B

Qwen/Qwen3-8B
macOSiOS
Qwen 2 presets
Family
qwen3
Context
40K
Compression
4bit, none

Qwen3.5-0.8B

Qwen/Qwen3.5-0.8B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.5-2B

Qwen/Qwen3.5-2B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.5-4B

Qwen/Qwen3.5-4B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.5-9B

Qwen/Qwen3.5-9B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.5-27B

Qwen/Qwen3.5-27B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.5-35B-A3B

Qwen/Qwen3.5-35B-A3B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.5-122B-A10B

Qwen/Qwen3.5-122B-A10B
macOS
Qwen 1 preset
Family
qwen3.5
Context
256K
Compression
none

Qwen3.6-27B

Qwen/Qwen3.6-27B
macOS
Qwen 1 preset
Family
qwen3.6
Context
256K
Compression
none

Qwen3.6-35B-A3B

Qwen/Qwen3.6-35B-A3B
macOS
Qwen 1 preset
Family
qwen3.6
Context
256K
Compression
none

Qwen3.8-27B

Qwen/Qwen3.8-27B
macOS
Qwen 1 preset
Family
qwen3.8
Context
256K
Compression
none

SmolLM2-1.7B-Instruct

HuggingFaceTB/SmolLM2-1.7B-Instruct
macOSiOS
Hugging Face 2 presets
Family
smollm2
Context
8K
Compression
4bit, none

SmolLM2-135M-Instruct

HuggingFaceTB/SmolLM2-135M-Instruct
macOSiOS
Hugging Face 2 presets
Family
smollm2
Context
8K
Compression
none

SmolLM2-360M-Instruct

HuggingFaceTB/SmolLM2-360M-Instruct
macOSiOS
Hugging Face 2 presets
Family
smollm2
Context
8K
Compression
none