Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.
DeepSeek-R1-Distill-Qwen-32B-Japanese
cyberagent · 33B · mit
MLX
Quant4-bit / 8-bit
Memory23 GB
Downloads549
Added27 Jan 2025
MiniCPM-o-4_5
MLX Community · 9B · apache-2.0
MLX
Quant4-bit / 5-bit
Memory9 GB
Downloads548
Added5 Mar 2026
Kimi-K2.7-Code
Moonshot AI · 1.0T · modified-mit
MLX
Quant8-bit
Memory1221 GB
Downloads548
Added15 Jun 2026
Dolphin3.0-R1-Mistral-24B
dphn · 24B
MLX
Quant4-bit / 6-bit
Memory17 GB
Downloads547
Added16 Feb 2025
Mixtral-8x7B-Instruct-v0.1
MLX Community · 47B · apache-2.0
MLX
Quant4-bit / 8-bit
Memory32 GB
Downloads547
Added20 Dec 2023
GLM-4.5V
Z.ai · 108B · mit
MLX
Quant4-bit / MXFP4 …
Memory72 GB
Downloads540
Added24 Aug 2025
Qwythos-9B-v2
empero-ai · 9B · apache-2.0
MLX
Quant4-bit
Memory9 GB
Downloads538
Added14 Jul 2026
mel-roformer-kim-vocal-2
MLX Community · 228M · mit
MLX
Quant—
Memory3 GB
Downloads538
Added25 Apr 2026
LightOnOCR-2-1B
MLX Community · 1B · apache-2.0
MLX
Quant4-bit / 8-bit …
Memory4 GB
Downloads534
Added26 Jan 2026
Meta-Llama-3-70B-Instruct
MLX Community · 71B · llama3
MLX
Quant4-bit / 8-bit
Memory47 GB
Downloads533
Added18 Apr 2024
bitnet-b1.58-2B-4T
Microsoft · 1.1B · mit
MLX
Quant4-bit / 6-bit …
Memory3 GB
Downloads530
Added10 Jun 2025
GLM-4.7-REAP-50
MLX Community · 185B · apache-2.0
MLX
QuantMXFP4
Memory119 GB
Downloads529
Added3 Jan 2026
Huihui-Qwen3.5-35B-A3B-abliterated
huihui-ai · 35B · apache-2.0
MLX
QuantMXFP4 / 6-bit
Memory24 GB
Downloads524
Added4 Mar 2026
ThinkingCap-Qwen3.6-27BTrending
bottlecapai · 27B · apache-2.0
MLX
Quant4-bit / 6-bit
Memory20 GB
Downloads522
Added14 Jul 2026
LFM2.5-Audio-1.5B
MLX Community · 1.5B · lfm1.0
MLX
Quant4-bit / 5-bit …
Memory4 GB
Downloads522
Added8 Jan 2026
MiniMax-M2.5
MiniMax · 229B · modified-mit
MLX
Quant3-bit / 4-bit …
Memory114 GB
Downloads518
Added13 Feb 2026
Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1
Goekdeniz-Guelmez · 8.2B
MLX
Quant4-bit / 8-bit …
Memory8 GB
Downloads513
Added29 May 2025
Ming-3.0-audio-tiny
inclusionAI · 8.6B · mit
MLX
Quant4-bit / 8-bit …
Memory9 GB
Downloads512
Added19 Oct 2026
Phi-4-mini-reasoning
Microsoft · 3.8B · mit
MLX
Quant4-bit / 6-bit …
Memory5 GB
Downloads511
Added1 May 2025
deepseek-vl2-tiny
MLX Community · 3.4B · deepseek
MLX
Quant3-bit / 4-bit …
Memory4 GB
Downloads507
Added22 Dec 2024
Irodori-TTS-v4.1-Small
Aratako · 766M
MLX
Quant8-bit / fp16
Memory4 GB
Downloads502
Added15 Aug 2026
Josiefied-Qwen2.5-14B-Instruct-abliterated-v4
Goekdeniz-Guelmez · 15B · apache-2.0
MLX
Quant2-bit / 4-bit …
Memory8 GB
Downloads502
Added9 Dec 2024
olmOCR-7B-0225-preview
MLX Community · 8.3B · apache-2.0
MLX
Quant4-bit / 6-bit …
Memory9 GB
Downloads502
Added3 Mar 2025
QwQ-32B-Preview
Alibaba Qwen · 33B · apache-2.0
MLX
Quant2-bit / 3-bit …
Memory14 GB
Downloads502
Added27 Nov 2024
Load more models Showing 576 of 2,335 · Previous page