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-20bTrending
OpenAI · 21B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4
Memory16 GB
Downloads178K
Added29 Aug 2025
Qwen3.8-27BTrending
Alibaba Qwen · 28B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory3 GB
Downloads169K
Added14 Aug 2026
Qwen3.5-4BTrending
Alibaba Qwen · 4.7B · apache-2.0
MLXCore AI
Quant4-bit / 5-bit …
Memory3 GB
Downloads111K
Added2 Mar 2026
Qwen3-0.6B
Alibaba Qwen · 752M · apache-2.0
MLXCore AI
Quant3-bit / 4-bit …
Memory3 GB
Downloads91K
Added28 Apr 2025
Qwen3.6-35B-A3BTrending
Alibaba Qwen · 36B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory3 GB
Downloads57K
Added16 Apr 2026
Qwen3.6-27B
Alibaba Qwen · 28B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory3 GB
Downloads55K
Added22 Apr 2026
Qwen3-8BTrending
Alibaba Qwen · 8.2B · apache-2.0
MLXCore AI
Quant3-bit / 4-bit …
Memory7 GB
Downloads36K
Added28 Apr 2025
Qwen3.5-9BTrending
Alibaba Qwen · 9.7B · apache-2.0
MLXCore AI
Quant4-bit / 5-bit …
Memory3 GB
Downloads36K
Added2 Mar 2026
Qwen3-4B
Alibaba Qwen · 4B · apache-2.0
MLXCore AI
Quant3-bit / 4-bit …
Memory4 GB
Downloads32K
Added28 Apr 2025
gemma-4-E4B-it
Google · 8B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory8 GB
Downloads31K
Added2 Apr 2026
gemma-4-E2B-itTrending
Google · 5.1B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory5 GB
Downloads29K
Added2 Apr 2026
Qwen3-Coder-30B-A3B-InstructTrending
Alibaba Qwen · 31B · apache-2.0
MLXCore AI
Quant3-bit / 4-bit …
Memory17 GB
Downloads27K
Added31 Jul 2025
Qwen3-1.7B
Alibaba Qwen · 2B · apache-2.0
MLXCore AI
Quant3-bit / 4-bit …
Memory3 GB
Downloads19K
Added28 Apr 2025
Muse-Glimmer-30B
meta-models · 30B · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory24 GB
Downloads17K
Added10 Aug 2026
Qwen3.5-2B
Alibaba Qwen · 2.3B · apache-2.0
MLXCore AI
Quant4-bit / 8-bit …
Memory4 GB
Downloads14K
Added2 Mar 2026
embeddinggemma-2
Google · 744M · apache-2.0
MLXCore AI
Quant4-bit / MXFP4 …
Memory4 GB
Downloads14K
Added6 Oct 2026
Qwen3.5-0.8B
Alibaba Qwen · 873M · apache-2.0
MLXCore AI
Quant4-bit / 8-bit …
Memory3 GB
Downloads7.6K
Added2 Mar 2026
Phi-4-mini-instructTrending
Microsoft · 3.8B · mit
MLXCore AI
Quant4-bit / 6-bit …
Memory5 GB
Downloads4.8K
Added27 Feb 2025
SmolLM2-135M-Instruct
Hugging Face · 135M · apache-2.0
MLXCore AI
QuantNone
Memory3 GB
Downloads4.0K
Added31 Oct 2024
gemma-3n-E2B-it
Google · 5.4B · gemma
MLXCore AI
Quant4-bit / 4-bit DWQ …
Memory5 GB
Downloads2.7K
Added29 Jun 2025
gemma-3n-E4B-it
Google · 7.8B · gemma
MLXCore AI
Quant4-bit / 4-bit DWQ …
Memory7 GB
Downloads1.6K
Added29 Jun 2025
Qwen3.5-122B-A10BTrending
Alibaba Qwen · 125B · apache-2.0
MLXCore AI
Quant2-bit / MXFP4 …
Memory46 GB
Downloads1.5K
Added14 Apr 2026
Qwen3.5-27B
Alibaba Qwen · 28B · apache-2.0
MLXCore AI
Quant4-bit / MXFP8
Memory20 GB
Downloads1.2K
Added4 Mar 2026
SmolLM2-360M-Instruct
Hugging Face · 362M · apache-2.0
MLXCore AI
Quant6-bit / bf16
Memory3 GB
Downloads869
Added31 Oct 2024
Load more models Showing 24 of 43