Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

296 builds · page 5 of 5 · clear filters

Qwen2.5-72B-Instruct-4bit-AWQ

from Qwen/Qwen2.5-72B-Instruct
4-bit
Text generation · Qwen ↓ 57 · ♥ 1
Params
73B
Weights
≈ 40.9 GB
Mac memory
48 GB+

qwen · updated 2025-04-26

Qwen3-30B-A3B-4bit-DWQ-10072025

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 56 · ♥ 2
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-10

Qwen_QwQ-32B-Preview_MLX-4bit

from Qwen/QwQ-32B-Preview
4-bit
Text generation · Qwen ↓ 56 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2024-11-28

QwQ-32B-Preview-bf16

from Qwen/QwQ-32B-Preview
bf16
Text generation · Qwen ↓ 55 · ♥ 5
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2024-11-27

Qwen-AgentWorld-35B-A3B-oQ3.5

from Qwen/Qwen-AgentWorld-35B-A3B
3-bit
Text generation · Qwen ↓ 55 · ♥ 0
Params
35B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-06-27

Qwen2.5-Math-7B-Instruct-8bit

from Qwen/Qwen2.5-Math-7B-Instruct
8-bit
Text generation · Qwen ↓ 55 · ♥ 0
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-03

Qwen3-30B-A3B-4bit-DWQ-05082025

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 53 · ♥ 4
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-08

Qwen2.5-Math-72B-Instruct-8bit

from Qwen/Qwen2.5-Math-72B
8-bit
Text generation · Qwen ↓ 53 · ♥ 0
Params
73B
Weights
≈ 77.3 GB
Mac memory
96 GB+

qwen · updated 2024-09-19

Qwen3-0.6B-4bit-DWQ-05092025

from Qwen/Qwen3-0.6B
4-bit DWQ
Text generation · Qwen ↓ 53 · ♥ 0
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-10

QwQ-32B-3bit

from Qwen/QwQ-32B
3-bit
Text generation · Qwen ↓ 52 · ♥ 0
Params
33B
Weights
≈ 14.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-05

Qwen3-32B-bf16

from Qwen/Qwen3-32B
bf16
Text generation · Qwen ↓ 51 · ♥ 1
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-04-28

Qwen3.6-27B-MTP-5bit

from Qwen/Qwen3.6-27B
5-bit
Text generation · Qwen ↓ 49 · ♥ 1
Params
425M
Weights
≈ 292 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

QwQ-32B-bf16

from Qwen/QwQ-32B
bf16
Text generation · Qwen ↓ 48 · ♥ 9
Params
33B
Weights
≈ 65.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-03-05

Qwen3-30B-A3B-4bit-DWQ-053125

from Qwen/Qwen3-30B-A3B
4-bit DWQ
Text generation · Qwen ↓ 47 · ♥ 7
Params
31B
Weights
≈ 17.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-02

Qwen3-4B-Instruct-2507-5.0bpw-dynamic

from Qwen/Qwen3-4B-Instruct-2507
4-bit
Text generation · Qwen ↓ 47 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-11

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr9e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 46 · ♥ 1
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

qwen2.5-0.5b-instruct-q2

from Qwen/Qwen2.5-0.5B-Instruct
2-bit
Text generation · Qwen ↓ 46 · ♥ 0
Params
494M
Weights
≈ 155 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-09

Qwen3-235B-A22B-Instruct-2507-6bit

from Qwen/Qwen3-235B-A22B-Instruct-2507
6-bit
Text generation · Qwen ↓ 45 · ♥ 0
Params
235B
Weights
≈ 191 GB
Mac memory
256 GB+

apache-2.0 · updated 2025-07-22

Qwen3-0.6B-Base

from Qwen/Qwen3-0.6B-Base
Text generation · Qwen ↓ 44 · ♥ 0
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-27

Qwen2.5-Math-1.5B-bf16

from Qwen/Qwen2.5-1.5B
bf16
Text generation · Qwen ↓ 43 · ♥ 0
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Qwen2.5-Math-7B-Instruct

from Qwen/Qwen2.5-Math-7B-Instruct
Text generation · Qwen ↓ 43 · ♥ 0
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-03

Qwen3-235B-A22B-3bit

from Qwen/Qwen3-235B-A22B
3-bit
Text generation · Qwen ↓ 41 · ♥ 1
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-05-01

Qwen3-Next-80B-A3B-Thinking-5bit

from Qwen/Qwen3-Next-80B-A3B-Thinking
5-bit
Text generation · Qwen ↓ 41 · ♥ 1
Params
80B
Weights
≈ 54.8 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-09-13

Qwen3-235B-A22B-Thinking-2507-3bit-DWQ

from Qwen/Qwen3-235B-A22B-Thinking-2507
3-bit DWQ
Text generation · Qwen ↓ 40 · ♥ 6
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-07-26

Qwen3-30B-A3B-Instruct-2507-bf16

from Qwen/Qwen3-30B-A3B-Instruct-2507
bf16
Text generation · Qwen ↓ 39 · ♥ 0
Params
31B
Weights
≈ 61.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-08-01

Qwen3-235B-A22B-3bit-DWQ

from Qwen/Qwen3-235B-A22B
3-bit DWQ
Text generation · Qwen ↓ 38 · ♥ 5
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-05-15

A.X-4.0-Light-MLX-BF16

from Qwen/Qwen2.5-7B
bf16
Text generation · Qwen ↓ 38 · ♥ 1
Params
7.3B
Weights
≈ 14.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-01-20

Qwen3-4B-Thinking-2507-5bit

from Qwen/Qwen3-4B-Thinking-2507
5-bit
Text generation · Qwen ↓ 38 · ♥ 1
Params
4.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-4B-Thinking-2507-fp16

from Qwen/Qwen3-4B-Thinking-2507
fp16
Text generation · Qwen ↓ 38 · ♥ 1
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-10-10

Qwen2.5-Math-1.5B-8bit

from Qwen/Qwen2.5-1.5B
8-bit
Text generation · Qwen ↓ 38 · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Qwen2.5-Math-1.5B-Instruct-bf16

from Qwen/Qwen2.5-Math-1.5B
bf16
Text generation · Qwen ↓ 37 · ♥ 0
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Qwen2.5-Math-1.5B-4bit

from Qwen/Qwen2.5-1.5B
4-bit
Text generation · Qwen ↓ 35 · ♥ 0
Params
1.5B
Weights
≈ 869 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr5e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 35 · ♥ 0
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen2.5-Math-1.5B-Instruct-8bit

from Qwen/Qwen2.5-Math-1.5B
8-bit
Text generation · Qwen ↓ 34 · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-09-18

Qwen3-235B-A22B-Thinking-2507-4bit-DWQ

from Qwen/Qwen3-235B-A22B-Thinking-2507
4-bit DWQ
Text generation · Qwen ↓ 33 · ♥ 4
Params
235B
Weights
≈ 132 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-07-27

Qwen3-4B-4bit-DWQ-calibration-1332

from Qwen/Qwen3-4B
4-bit DWQ
Text generation · Qwen ↓ 33 · ♥ 0
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-05-11

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 31 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-4B-Thinking-2507-6bit

from Qwen/Qwen3-4B-Thinking-2507
6-bit
Text generation · Qwen ↓ 31 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-08-06

Qwen3-235B-A22B-Thinking-2507-3bit

from Qwen/Qwen3-235B-A22B-Thinking-2507
3-bit
Text generation · Qwen ↓ 30 · ♥ 1
Params
235B
Weights
≈ 103 GB
Mac memory
128 GB+

apache-2.0 · updated 2025-07-25

Qwen2.5-Math-72B-Instruct-bf16

from Qwen/Qwen2.5-Math-72B
bf16
Text generation · Qwen ↓ 30 · ♥ 0
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+

qwen · updated 2024-09-19

Qwen3-30B-4bit-DWQ-053125

from Qwen/Qwen3-32B
4-bit DWQ
Text generation · Qwen ↓ 30 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-02

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr2e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 30 · ♥ 0
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr3e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 30 · ♥ 0
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

QwQ-32b-4bit-DWQ

from Qwen/QwQ-32B
4-bit DWQ
Text generation · Qwen ↓ 28 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-26

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr3e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 28 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-30B-A3B-Instruct-2507-5bit-DWQ-lr1e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
5-bit DWQ
Text generation · Qwen ↓ 27 · ♥ 0
Params
31B
Weights
≈ 21.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr8e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 27 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-08-02

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr8e-8

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 27 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-235B-A22B-Thinking-2507-mixed-3-5bit

from Qwen/Qwen3-235B-A22B-Thinking-2507
5-bit
Text generation · Qwen ↓ 25 · ♥ 1
Params
235B
Weights
≈ 162 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-07-25

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr5e-9

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 25 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-08-02

Qwen3-235B-A22B-mixed-3-6bit

from Qwen/Qwen3-235B-A22B
6-bit
Text generation · Qwen ↓ 24 · ♥ 2
Params
235B
Weights
≈ 191 GB
Mac memory
256 GB+

apache-2.0 · updated 2025-05-09

Qwen3-235B-A22B-Thinking-2507-5bit

from Qwen/Qwen3-235B-A22B-Thinking-2507
5-bit
Text generation · Qwen ↓ 23 · ♥ 0
Params
235B
Weights
≈ 162 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-07-25

Qwen3-235B-A22B-mixed-3-4bit

from Qwen/Qwen3-235B-A22B
4-bit
Text generation · Qwen ↓ 23 · ♥ 0
Params
235B
Weights
≈ 132 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-05-08