Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.
OpenCodeInterpreter-DS-33B-hf
Downloads, 30 days
215
Memory needed (est.)
24 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 24 Feb 2024
Llama-4-Maverick-17B-128E
Downloads, 30 days
214
Memory needed (est.)
—
Quantisation
4-bit, 6-bit
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
llama4Added 7 Apr 2025
EXAONE-3.5-2.4B-Instruct
Downloads, 30 days
214
Memory needed (est.)
3 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 9 Dec 2024
ERNIE-4.5-VL-28B-A3B-Thinking
Downloads, 30 days
213
Memory needed (est.)
22 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Jan 2026
Mellum-4b-base
Downloads, 30 days
212
Memory needed (est.)
5 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 28 Jun 2025
dolphin-2.7-mixtral-8x7b
Downloads, 30 days
212
Memory needed (est.)
32 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 6 Apr 2024
Hy-MT2-1.8B
Downloads, 30 days
212
Memory needed (est.)
5 GB
Quantisation
8-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Jun 2026
Falcon-H1-1.5B-Instruct
Downloads, 30 days
212
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
falcon-llm-licenseAdded 14 Jun 2025
Molmo2-8B
Downloads, 30 days
211
Memory needed (est.)
10 GB
Quantisation
MXFP4
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 20 Oct 2026
deepseek-vl-7b-chat
Downloads, 30 days
211
Memory needed (est.)
7 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
deepseekAdded 8 Jun 2024
Cydonia-24B-v3
Downloads, 30 days
211
Memory needed (est.)
17 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
otherAdded 4 Jun 2025
BTL-4
Downloads, 30 days
210
Memory needed (est.)
24 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 6 Aug 2026
aya-vision-8b
Downloads, 30 days
210
Memory needed (est.)
7 GB
Quantisation
3-bit, 4-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
cc-by-nc-4.0Added 5 Mar 2025
gemma-4-e4b-it-4bit-MAD
Downloads, 30 days
210
Memory needed (est.)
7 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 4 May 2026
Meta-Llama-3-8B
Downloads, 30 days
210
Memory needed (est.)
8 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3Added 18 Apr 2024
Josiefied-Hermes-3-Llama-3.2-3B-v1
Downloads, 30 days
208
Memory needed (est.)
5 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
Licence not statedAdded 28 Oct 2025
CodeLlama-70b-Instruct-hf
Downloads, 30 days
208
Memory needed (est.)
—
Quantisation
4-bit
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
llama2Added 29 Jan 2024
Hermes-3-Llama-3.1-8B
Downloads, 30 days
208
Memory needed (est.)
6 GB
Quantisation
3-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3Added 13 Dec 2024
GLM-5.1
Downloads, 30 days
208
Memory needed (est.)
886 GB
Quantisation
8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 12 Apr 2026
deepseek-coder-33b-instruct
Downloads, 30 days
207
Memory needed (est.)
23 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
deepseekAdded 21 Jun 2025
AMD-Llama-135m
Downloads, 30 days
206
Memory needed (est.)
3 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 3 Oct 2024
NVIDIA-Nemotron-3-Nano-30B-A3B-OptiQ
Downloads, 30 days
206
Memory needed (est.)
8 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
nvidia-open-model-licenseAdded 4 Jun 2026
whisper-large
Downloads, 30 days
206
Memory needed (est.)
—
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
Licence not statedAdded 9 Mar 2024
whisper-tiny.en-asr
Downloads, 30 days
206
Memory needed (est.)
3 GB
Quantisation
4-bit, 5-bit, 6-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 15 Jan 2026
Load more models Showing 888 of 2,335 · Previous page