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 · 7.1B
llava-1.5-7b
MLX Text · Vision
Downloads, 30 days
6.8K
Memory needed (est.)
7 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
llama2Added 23 Apr 2024
RecursiveSI · 40BTrending
flint
MLX Text
Downloads, 30 days
6.6K
Memory needed (est.)
16 GB
Quantisation
2-bit, 3-bit, 4-bit +3
Devices
Runs on: Mac
apache-2.0Added 24 Oct 2026
MLX Community · 23M
all-MiniLM-L6-v2
MLX Text
Downloads, 30 days
6.6K
Memory needed (est.)
3 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
apache-2.0Added 2 Apr 2025
OpenAI · 117BTrending
gpt-oss-120b
MLX Text
Downloads, 30 days
6.3K
Memory needed (est.)
76 GB
Quantisation
MXFP4
Devices
Runs on: Mac
apache-2.0Added 29 Aug 2025
MLX Community · 12B
Mistral-Nemo-Instruct-2407
MLX
Downloads, 30 days
6.3K
Memory needed (est.)
10 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
apache-2.0Added 18 Jul 2024
MLX Community · 1.6B
LFM2-VL-1.6B
MLX Text · Vision
Downloads, 30 days
6.3K
Memory needed (est.)
4 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
lfm1.0Added 16 Aug 2025
openbmb · 35B
MiniCPM-V-4.7-35B-A3B
MLX Text · Vision
Downloads, 30 days
6.2K
Memory needed (est.)
26 GB
Quantisation
4-bit, MXFP4, 5-bit +4
Devices
Runs on: Mac
apache-2.0Added 13 Oct 2026
Alibaba Qwen · 235B
Qwen3-235B-A22B
MLX Text
Downloads, 30 days
6.1K
Memory needed (est.)
117 GB
Quantisation
3-bit, 3-bit DWQ, 4-bit +2
Devices
Runs on: Mac
apache-2.0Added 29 Apr 2025
DavidAU · 39B
Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking
MLX Text
Downloads, 30 days
6.1K
Memory needed (est.)
49 GB
Quantisation
8-bit
Devices
Runs on: Mac
apache-2.0Added 2 May 2026
MLX Community · 3.8B
Phi-3.5-mini-instruct
MLX Text
Downloads, 30 days
6.1K
Memory needed (est.)
3 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
mitAdded 20 Aug 2024
Alibaba Qwen · 235B
Qwen3-235B-A22B-Instruct-2507
MLX Text
Downloads, 30 days
6.0K
Memory needed (est.)
117 GB
Quantisation
3-bit, 4-bit, 5-bit +2
Devices
Runs on: Mac
apache-2.0Added 22 Jul 2025
MLX Community · 25B
gemma-4-26B-A4B-it-qat-OptiQ
MLX Text
Downloads, 30 days
6.0K
Memory needed (est.)
20 GB
Quantisation
4-bit
Devices
Runs on: Mac
apache-2.0Added 16 Jun 2026
Liquid AI · 1.2B
LFM2.5-1.2B-Instruct
MLX Text
Downloads, 30 days
5.9K
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
lfm1.0Added 6 Jan 2026
BAAI · 568M
bge-m3
MLX Text
Downloads, 30 days
5.7K
Memory needed (est.)
3 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
mitAdded 16 Mar 2026
DeepSeek · 1.8B
DeepSeek-R1-Distill-Qwen-1.5B
MLX Text
Downloads, 30 days
5.7K
Memory needed (est.)
3 GB
Quantisation
3-bit, 4-bit, 6-bit +3
Devices
Runs on: Mac
mitAdded 20 Jan 2025
NVIDIA · 623M
parakeet-tdt_ctc-0.6b-ja
MLX Audio
Downloads, 30 days
5.6K
Memory needed (est.)
5 GB
Quantisation
—
Devices
Runs on: Mac
cc-by-4.0Added 6 May 2025
Alibaba Qwen · 1.5B
Qwen2.5-Coder-1.5B
MLX Text
Downloads, 30 days
5.6K
Memory needed (est.)
3 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
apache-2.0Added 18 Sept 2024
MLX Community · 12BTrending
gemma-4-12B-it-qat-OptiQ
MLX Text
Downloads, 30 days
5.6K
Memory needed (est.)
10 GB
Quantisation
4-bit
Devices
Runs on: Mac
apache-2.0Added 15 Jun 2026
MLX Community · 27B
Qwen3.5-27B-Claude-4.6-Opus-Distilled
MLX
Downloads, 30 days
5.6K
Memory needed (est.)
19 GB
Quantisation
4-bit, 6-bit
Devices
Runs on: Mac
apache-2.0Added 4 Mar 2026
MLX Community · 27B
Qwen3.5-27B
MLX Text · Vision
Downloads, 30 days
5.5K
Memory needed (est.)
19 GB
Quantisation
4-bit, 4-bit DWQ, 5-bit +3
Devices
Runs on: Mac
apache-2.0Added 24 Feb 2026
MLX Community · 20M
snac_24khz
MLX
Downloads, 30 days
5.4K
Memory needed (est.)
3 GB
Quantisation
—
Devices
Runs on: Mac
mitAdded 22 Mar 2025
Google · 3.9B
translategemma-4b-it
MLX Text
Downloads, 30 days
5.3K
Memory needed (est.)
5 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
gemmaAdded 15 Jan 2026
Alibaba Qwen
Qwen-Image
MLX Image
Downloads, 30 days
5.2K
Memory needed (est.)
—
Quantisation
8-bit
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
apache-2.0Added 1 Jan 2026
DeepSeek · 7.6B
DeepSeek-R1-Distill-Qwen-7B
MLX Text
Downloads, 30 days
5.2K
Memory needed (est.)
6 GB
Quantisation
3-bit, 4-bit, 6-bit +3
Devices
Runs on: Mac
mitAdded 20 Jan 2025
Showing 144 of 2,334 ·