MLX models

2,334 matches

Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.

MLX Community · 2BTrending
Qwen3-ASR-1.7B
MLX
Downloads, 30 days
21K
Memory needed (est.)
4 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
apache-2.0Added 29 Jan 2026
MLX Community · 5B
gemma-3-4b-it
MLX Text · Vision
Downloads, 30 days
21K
Memory needed (est.)
6 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
gemmaAdded 12 Mar 2025
MLX Community · 3.8B
Ministral-3-3B-Instruct-2512
MLX
Downloads, 30 days
21K
Memory needed (est.)
6 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
apache-2.0Added 3 Dec 2025
MLX Community · 2.2B
Qwen2-VL-2B-Instruct
MLX Text · Vision
Downloads, 30 days
20K
Memory needed (est.)
4 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
apache-2.0Added 27 Sept 2024
MLX Community
gemma-3-27b-it-qat
MLX Text · Vision
Downloads, 30 days
20K
Memory needed (est.)
—
Quantisation
3-bit, 4-bit, 6-bit +1
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
qwenAdded 15 Apr 2025
MLX Community · 4.4B
Qwen3-VL-4B-Instruct
MLX Text · Vision
Downloads, 30 days
20K
Memory needed (est.)
5 GB
Quantisation
3-bit, 4-bit, 5-bit +2
Devices
Runs on: Mac
apache-2.0Added 14 Oct 2025
Alibaba Qwen
Qwen-Image-2512
MLX Image
Downloads, 30 days
20K
Memory needed (est.)
—
Quantisation
3-bit, 4-bit, 5-bit +1
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 1 Jan 2026
MLX Community · 13B
gemma-3-12b-it-qat
MLX Text · Vision
Downloads, 30 days
20K
Memory needed (est.)
32 GB
Quantisation
3-bit, 4-bit, 6-bit +2
Devices
Runs on: Mac
qwenAdded 15 Apr 2025
Alibaba Qwen · 2B
Qwen3-1.7B
MLXCore AI Text
Downloads, 30 days
19K
Memory needed (est.)
3 GB
Quantisation
3-bit, 4-bit, 4-bit DWQ +5
Devices
Runs on: Mac, iPhone
apache-2.0Added 28 Apr 2025
MLX Community · 9.2B
gemma-2-9b-it
MLX Text
Downloads, 30 days
19K
Memory needed (est.)
8 GB
Quantisation
4-bit, 8-bit, fp16
Devices
Runs on: Mac
gemmaAdded 27 Jun 2024
Black Forest Labs · 3.9B
FLUX.2-klein-4B
MLXCore AI Image
Downloads, 30 days
18K
Memory needed (est.)
5 GB
Quantisation
3-bit, 4-bit, 5-bit +3
Devices
Runs on: Mac
apache-2.0Added 23 May 2026
MLX Community · 13B
gemma-3-12b-it
MLX Text · Vision
Downloads, 30 days
17K
Memory needed (est.)
32 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
gemmaAdded 12 Mar 2025
MLX Community · 906M
Qwen3-TTS-12Hz-0.6B-CustomVoice
MLX Audio
Downloads, 30 days
17K
Memory needed (est.)
4 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
apache-2.0Added 22 Jan 2026
meta-models · 30B
Muse-Glimmer-30B
MLXCore AI Text · Vision
Downloads, 30 days
17K
Memory needed (est.)
24 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
apache-2.0Added 10 Aug 2026
MLX Community · 2.3B
gemma-4-E2B-it-qat-mobile
MLX Text · Vision
Downloads, 30 days
17K
Memory needed (est.)
5 GB
Quantisation
8-bit
Devices
Runs on: Mac
Licence not statedAdded 29 Jul 2026
MLX Community · 7.2B
Mistral-7B-Instruct-v0.3
MLX
Downloads, 30 days
16K
Memory needed (est.)
7 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
apache-2.0Added 22 May 2024
MLX Community
whisper-medium
MLX Audio
Downloads, 30 days
16K
Memory needed (est.)
—
Quantisation
4-bit, 8-bit, fp32
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Jan 2024
MLX Community
whisper-small.en
MLX
Downloads, 30 days
16K
Memory needed (est.)
—
Quantisation
4-bit, 8-bit, fp32
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 8 Mar 2024
ResembleAI · 693M
chatterbox
MLX Audio
Downloads, 30 days
16K
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
apache-2.0Added 1 Dec 2025
meta-models · 822B
Muse-Spark-Open-816B-A42B
MLX Text · Vision
Downloads, 30 days
16K
Memory needed (est.)
411 GB
Quantisation
3-bit, 4-bit
Devices
Runs on: Mac
muse-model-licenseAdded 15 Oct 2026
OpenAI · 809M
whisper-large-v3-turbo
MLXCore AI Audio
Downloads, 30 days
16K
Memory needed (est.)
3 GB
Quantisation
4-bit, 8-bit, fp16
Devices
Runs on: Mac, iPhone
mitAdded 14 Dec 2025
Google · 31B
gemma-4-31B-it
MLX Text · Vision
Downloads, 30 days
15K
Memory needed (est.)
10 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
apache-2.0Added 2 Apr 2026
openbmb · 2.4BTrending
VoxCPM2
MLX Audio
Downloads, 30 days
15K
Memory needed (est.)
5 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
apache-2.0Added 8 Apr 2026
Alibaba Qwen · 235B
Qwen3-235B-A22B-Thinking-2507
MLX Text
Downloads, 30 days
15K
Memory needed (est.)
117 GB
Quantisation
3-bit, 3-bit DWQ, 4-bit +3
Devices
Runs on: Mac
apache-2.0Added 25 Jul 2025
Showing 72 of 2,334 ·