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 11m 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

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

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

Compression

4bit, none

Phi-3-mini-4k-instruct

microsoft/Phi-3-mini-4k-instruct

macOS

Microsoft · Phi 1 preset

Family

phi3

Context

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

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-Coder-30B-A3B-Instruct

Qwen/Qwen3-Coder-30B-A3B-Instruct

macOS

Qwen 1 preset

Family

qwen3

Context

256K

Compression

4bit

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

Compression

4bit, none

SmolLM2-135M-Instruct

HuggingFaceTB/SmolLM2-135M-Instruct

macOSiOS

Hugging Face 2 presets

Family

smollm2

Context

Compression

none

SmolLM2-360M-Instruct

HuggingFaceTB/SmolLM2-360M-Instruct

macOSiOS

Hugging Face 2 presets

Family

smollm2

Context

Compression

none

Image and video generation 4

FLUX.2-klein-4B

black-forest-labs/FLUX.2-klein-4B

black-forest-labs 1 preset

Family

flux2

Context

—

Compression

4bit

Sana_Sprint_0.6B_1024px_diffusers

Efficient-Large-Model/Sana_Sprint_0.6B_1024px_diffusers

Efficient-Large-Model 1 preset

Family

sana-sprint

Context

—

Compression

t8bit-te4bit-asym

Sana_Sprint_1.6B_1024px_diffusers

Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers

Efficient-Large-Model 1 preset

Family

sana-sprint

Context

—

Compression

t8bit-te4bit-asym

Wan2.1-T2V-1.3B-Diffusers

Wan-AI/Wan2.1-T2V-1.3B-Diffusers

Wan-AI 1 preset

Family

wan

Context

—

Compression

none

Embeddings 3

clap-htsat-unfused

laion/clap-htsat-unfused

macOSiOS

laion 1 preset

Family

clap

Context

—

Compression

—

clip-vit-base-patch32

openai/clip-vit-base-patch32

macOSiOS

OpenAI · gpt-oss 1 preset

Family

clip

Context

—

Compression

—

embeddinggemma-2

google/embeddinggemma-2

macOSiOS

Google · Gemma 1 preset

Family

embeddinggemma

Context

—

Compression

—

Speech recognition 3

wav2vec2-base

wav2vec2_asr_base_960h

macOSiOS

wav2vec2 1 preset

Family

wav2vec2

Context

—

Compression

—

whisper-large-v3

openai/whisper-large-v3

macOSiOS

OpenAI · gpt-oss 1 preset

Family

whisper

Context

—

Compression

—

whisper-large-v3-turbo

openai/whisper-large-v3-turbo

macOSiOS

OpenAI · gpt-oss 1 preset

Family

whisper

Context

—

Compression

—

Object detection 2

yolos-base

hustvl/yolos-base

macOSiOS

hustvl 1 preset

Family

yolo

Context

—

Compression

—

yolos-tiny

hustvl/yolos-tiny

macOSiOS

hustvl 1 preset

Family

yolo

Context

—

Compression

—

Segmentation 3

efficient-sam-vitt

efficient_sam_vitt

macOSiOS

efficient-sam 1 preset

Family

efficient-sam

Context

—

Compression

—

sam3

facebook/sam3

macOSiOS

facebook 1 preset

Family

sam3

Context

—

Compression

—

sam3

facebook/sam3

macOSiOS

facebook 1 preset

Family

sam3_video

Context

—

Compression

—

Depth estimation 1

da3-small

depth-anything/da3-small

macOS

depth-anything 1 preset

Family

depth-anything

Context

—

Compression

—

Super-resolution 1

edsr-x2

edsr_r16f64_x2

macOSiOS

edsr 1 preset

Family

edsr

Context

—

Compression

—

Text encoders 4

roberta-base

macOSiOS

roberta 1 preset

Family

roberta

Context

—

Compression

—

t5-base

google-t5/t5-base

macOSiOS

google-t5 1 preset

Family

Context

—

Compression

—

t5-large

google-t5/t5-large

macOSiOS

google-t5 1 preset

Family

Context

—

Compression

—

t5-small

google-t5/t5-small

macOSiOS

google-t5 1 preset

Family

Context

—

Compression

—

Image classification 1

pvt-v2-b0

pvt_v2_b0

macOSiOS

pvt 1 preset

Family

pvt

Context

—

Compression

—