Models with MLX builds on mlx-community, ready to run on a Mac with Apple’s MLX framework.
Step-3.7-Flash
Downloads, 30 days
311
Memory needed (est.)
72 GB
Quantisation
2-bit, 3-bit, 4-bit +2
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 29 May 2026
Astrea-R8-Chat-9B
Downloads, 30 days
310
Memory needed (est.)
9 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 23 Oct 2026
gemma-3-4b-pt
Downloads, 30 days
309
Memory needed (est.)
6 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 12 Mar 2025
Qwen2.5-0.5B
Downloads, 30 days
309
Memory needed (est.)
3 GB
Quantisation
4-bit, 8-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 18 Sept 2024
Florence-2-large-ft
Downloads, 30 days
308
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
mitAdded 21 Nov 2024
MOSS-Audio-Tokenizer
Downloads, 30 days
307
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 31 Mar 2026
gpt-oss-20b-Ja-Fin-Thinking
Downloads, 30 days
306
Memory needed (est.)
16 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 27 Mar 2026
Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct
Downloads, 30 days
306
Memory needed (est.)
8 GB
Quantisation
4-bit, 6-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
cc-by-nc-4.0Added 30 Jun 2025
gemma-3-4b-it-abliterated
Downloads, 30 days
305
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
gemmaAdded 22 Mar 2025
Qwythos-27B-v1
Downloads, 30 days
304
Memory needed (est.)
20 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 3 Aug 2026
kanana-2-3b-instruct
Downloads, 30 days
301
Memory needed (est.)
4 GB
Quantisation
4-bit, 6-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
kanana-open-licenseAdded 4 Aug 2026
gemma-3-4b-it
Downloads, 30 days
297
Memory needed (est.)
5 GB
Quantisation
3-bit, 4-bit DWQ, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
gemmaAdded 15 Apr 2025
Qwopus3.8-27B-Flash
Downloads, 30 days
297
Memory needed (est.)
20 GB
Quantisation
MXFP4, MXFP8
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Sept 2026
NVIDIA-Nemotron-3-Nano-4B-BF16
Downloads, 30 days
290
Memory needed (est.)
11 GB
Quantisation
bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
nvidia-nemotron-open-model-licenseAdded 21 Mar 2026
Llama-3.3-Swallow-70B-Instruct-v0.4
Downloads, 30 days
290
Memory needed (est.)
47 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3.3Added 10 Mar 2025
Qwen2-57B-A14B-Instruct
Downloads, 30 days
288
Memory needed (est.)
39 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 6 Jun 2024
CodeLlama-7b-Python-hf
Downloads, 30 days
287
Memory needed (est.)
—
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
No memory estimate: size not published
8
16
24
32
64
128
llama2Added 3 Jan 2024
AI21-Jamba-Reasoning-3B
Downloads, 30 days
284
Memory needed (est.)
4 GB
Quantisation
4-bit, 6-bit, bf16
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Oct 2025
Llama-3.1-405B-Instruct
Downloads, 30 days
280
Memory needed (est.)
484 GB
Quantisation
8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
llama3.1Added 6 Nov 2024
GLM-Z1-9B-0414
Downloads, 30 days
280
Memory needed (est.)
8 GB
Quantisation
4-bit, 6-bit, 8-bit +1
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
mitAdded 17 Apr 2025
VulnLLM-R-7B
Downloads, 30 days
278
Memory needed (est.)
7 GB
Quantisation
4-bit, 6-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 2 Jan 2026
InternVL3_5-1B
Downloads, 30 days
278
Memory needed (est.)
4 GB
Quantisation
4-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 4 Oct 2025
Qwen3-VL-8B-Thinking
Downloads, 30 days
278
Memory needed (est.)
8 GB
Quantisation
3-bit, 4-bit, 5-bit +3
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 14 Oct 2025
Qwen2.5-Math-7B-Instruct
Downloads, 30 days
277
Memory needed (est.)
7 GB
Quantisation
4-bit, 8-bit
Devices
Runs on: Mac
Fits in unified memory
8
16
24
32
64
128
apache-2.0Added 18 Sept 2024
Load more models Showing 576 of 1,549 · Previous page