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

140 builds · page 2 of 3 · clear filters

Qwen3.6-27B-6bit

from Qwen/Qwen3.6-27B
6-bit
Vision + text · Qwen ↓ 213 · ♥ 9
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-22

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

from Qwen/Qwen2.5-VL-72B-Instruct
8-bit
Vision + text · Qwen ↓ 205 · ♥ 2
Params
73B
Weights
≈ 78.0 GB
Mac memory
96 GB+

qwen · updated 2025-02-25

Qwen2.5-VL-72B-Instruct-3bit

from Qwen/Qwen2.5-VL-72B-Instruct
3-bit
Vision + text · Qwen ↓ 200 · ♥ 5
Params
73B
Weights
≈ 33.2 GB
Mac memory
48 GB+

qwen · updated 2025-02-25

Qwen2.5-VL-3B-Instruct-bf16

from Qwen/Qwen2.5-VL-3B-Instruct
bf16
Vision + text · Qwen ↓ 178 · ♥ 4
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

updated 2025-02-26

Qwen2.5-VL-7B-Instruct-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 174 · ♥ 4
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-02-26

Qwen2.5-VL-7B-Instruct-3bit

from Qwen/Qwen2.5-VL-7B-Instruct
3-bit
Vision + text · Qwen ↓ 173 · ♥ 1
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-25

Qwen2.5-VL-7B-Instruct-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 166 · ♥ 3
Params
8.3B
Weights
≈ 6.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-25

Qwen3.5-397B-A17B-8bit

from Qwen/Qwen3.5-397B-A17B
8-bit
Vision + text · Qwen ↓ 165 · ♥ 5
Params
397B
Weights
≈ 422 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-02-20

Qwen2.5-VL-3B-Instruct-6bit

from Qwen/Qwen2.5-VL-3B-Instruct
6-bit
Vision + text · Qwen ↓ 156 · ♥ 3
Params
3.8B
Weights
≈ 3.2 GB
Mac memory
8 GB+

updated 2025-02-26

Qwen2.5-VL-3B-Instruct-3bit

from Qwen/Qwen2.5-VL-3B-Instruct
3-bit
Vision + text · Qwen ↓ 135 · ♥ 3
Params
3.8B
Weights
≈ 2.7 GB
Mac memory
8 GB+

updated 2025-02-25

Nanonets-OCR2-3B-8bit

from Qwen/Qwen2.5-VL-3B-Instruct
8-bit
Vision + text · Qwen ↓ 130 · ♥ 1
Params
3.8B
Weights
≈ 4.6 GB
Mac memory
8 GB+

updated 2025-10-14

Qwen3.5-122B-A10B-mxfp4

from Qwen/Qwen3.5-122B-A10B
MXFP4
Vision + text · Qwen ↓ 126 · ♥ 0
Params
123B
Weights
≈ 69.6 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-05-02

Molmo-7B-D-0924-4bit

from Qwen/Qwen2-7B
4-bit
Vision + text · Qwen ↓ 121 · ♥ 2
Params
8.0B
Weights
≈ 5.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-27

Qwen2.5-VL-72B-Instruct-6bit

from Qwen/Qwen2.5-VL-72B-Instruct
6-bit
Vision + text · Qwen ↓ 108 · ♥ 1
Params
73B
Weights
≈ 59.7 GB
Mac memory
96 GB+

qwen · updated 2025-02-25

MolmoPoint-8B-4bit

from Qwen/Qwen3-8B
4-bit
Vision + text · Qwen ↓ 108 · ♥ 0
Params
8.7B
Weights
≈ 7.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

Qwen3.5-2B-5bit

from Qwen/Qwen3.5-2B-Base
5-bit
Vision + text · Qwen ↓ 101 · ♥ 0
Params
2.2B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-02

Qwen3.6-27B-5bit

from Qwen/Qwen3.6-27B
5-bit
Vision + text · Qwen ↓ 100 · ♥ 2
Params
27B
Weights
≈ 19.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-22

Qwen2.5-VL-3B-Instruct-abliterated

from Qwen/Qwen2.5-VL-3B-Instruct
Vision + text · Qwen ↓ 99 · ♥ 1
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

updated 2025-02-25

Nanonets-OCR2-3B-4bit

from Qwen/Qwen2.5-VL-3B-Instruct
4-bit
Vision + text · Qwen ↓ 98 · ♥ 0
Params
3.8B
Weights
≈ 3.1 GB
Mac memory
8 GB+

updated 2025-10-14

Qwen3.6-27B-mxfp4

from Qwen/Qwen3.6-27B
MXFP4
Vision + text · Qwen ↓ 97 · ♥ 5
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-22

Nanonets-OCR2-3B-bf16

from Qwen/Qwen2.5-VL-3B-Instruct
bf16
Vision + text · Qwen ↓ 94 · ♥ 0
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

updated 2025-10-14

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

from Qwen/Qwen2.5-VL-72B-Instruct
bf16
Vision + text · Qwen ↓ 89 · ♥ 0
Params
73B
Weights
≈ 147 GB
Mac memory
192 GB+

qwen · updated 2025-02-25

Qwen3.5-122B-A10B-6bit-gs32

from Qwen/Qwen3.5-122B-A10B
6-bit
Vision + text · Qwen ↓ 86 · ♥ 1
Params
123B
Weights
≈ 100 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-05-02

Qwen2-VL-2B-mlx

from Qwen/Qwen2-VL-2B
Vision + text · Qwen ↓ 76 · ♥ 3
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-21

Nanonets-OCR-s-bf16

from Qwen/Qwen2.5-VL-3B-Instruct
bf16
Vision + text · Qwen ↓ 73 · ♥ 2
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

updated 2025-06-18

Qwen2-VL-7B-Instruct-abliterated-8bit

from Qwen/Qwen2-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 71 · ♥ 1
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-24

Qwen2-VL-7B-Instruct-abliterated-4bit

from Qwen/Qwen2-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 67 · ♥ 0
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-24

Molmo-7B-D-0924-8bit

from Qwen/Qwen2-7B
8-bit
Vision + text · Qwen ↓ 65 · ♥ 1
Params
8.0B
Weights
≈ 9.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-12-27

Molmo-7B-D-0924-bf16

from Qwen/Qwen2-7B
bf16
Vision + text · Qwen ↓ 59 · ♥ 1
Params
8.0B
Weights
≈ 16.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-01-01

Molmo-7B-D-0924-6bit

from Qwen/Qwen2-7B
6-bit
Vision + text · Qwen ↓ 58 · ♥ 0
Params
8.0B
Weights
≈ 7.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-12-27

Molmo-7B-D-0924-3bit

from Qwen/Qwen2-7B
3-bit
Vision + text · Qwen ↓ 56 · ♥ 0
Params
8.0B
Weights
≈ 4.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-27

MolmoPoint-8B-8bit

from Qwen/Qwen3-8B
8-bit
Vision + text · Qwen ↓ 55 · ♥ 0
Params
8.7B
Weights
≈ 10.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

MolmoPoint-8B-6bit

from Qwen/Qwen3-8B
6-bit
Vision + text · Qwen ↓ 52 · ♥ 0
Params
8.7B
Weights
≈ 9.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

Qwen2-VL-7B-Instruct-abliterated

from Qwen/Qwen2-VL-7B-Instruct
Vision + text · Qwen ↓ 51 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-24

MolmoPoint-8B-nvfp4

from Qwen/Qwen3-8B
4-bit
Vision + text · Qwen ↓ 50 · ♥ 0
Params
8.7B
Weights
≈ 7.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

Qwen2-VL-7B-Instruct-abliterated-6bit

from Qwen/Qwen2-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 48 · ♥ 0
Params
8.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-24

olmOCR-7B-0225-preview-4bit

from Qwen/Qwen2-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 45 · ♥ 1
Params
8.3B
Weights
≈ 5.6 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-03

MolmoPoint-8B-5bit

from Qwen/Qwen3-8B
5-bit
Vision + text · Qwen ↓ 45 · ♥ 0
Params
8.7B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

Nanonets-OCR2-3B-6bit

from Qwen/Qwen2.5-VL-3B-Instruct
6-bit
Vision + text · Qwen ↓ 42 · ♥ 0
Params
3.8B
Weights
≈ 3.8 GB
Mac memory
8 GB+

updated 2025-10-14

Holo1-3B-4bit

from Qwen/Qwen2.5-VL-3B-Instruct
4-bit
Vision + text · Qwen ↓ 41 · ♥ 1
Params
3.8B
Weights
≈ 3.1 GB
Mac memory
8 GB+

other · updated 2025-06-03

MolmoPoint-8B-mxfp4

from Qwen/Qwen3-8B
MXFP4
Vision + text · Qwen ↓ 38 · ♥ 0
Params
8.7B
Weights
≈ 7.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

Qwen-SEA-LION-v4-4B-VL-4bit

from Qwen/Qwen3-VL-4B-Instruct
4-bit
Vision + text · Qwen ↓ 37 · ♥ 0
Params
4.4B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-27

Qwen3.5-35B-A3B-GPTQ-Int4

from Qwen/Qwen3.5-35B-A3B
4-bit
Vision + text · Qwen ↓ 36 · ♥ 4
Params
7.0B
Weights
≈ 8.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-03

holo1.5-7b-mlx

from Qwen/Qwen2.5-VL-7B-Instruct
Vision + text · Qwen ↓ 36 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-09-17

QVQ-72B-Preview-4bit

from Qwen/Qwen2-VL-72B
4-bit
Vision + text · Qwen ↓ 34 · ♥ 7
Params
73B
Weights
≈ 41.3 GB
Mac memory
64 GB+

qwen · updated 2025-04-12

Holo1-3B-3bit

from Qwen/Qwen2.5-VL-3B-Instruct
3-bit
Vision + text · Qwen ↓ 34 · ♥ 1
Params
3.8B
Weights
≈ 2.7 GB
Mac memory
8 GB+

other · updated 2025-06-03

Holo1-7B-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 34 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-06-03

MolmoPoint-8B-fp16

from Qwen/Qwen3-8B
fp16
Vision + text · Qwen ↓ 34 · ♥ 0
Params
8.7B
Weights
≈ 17.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-03-21

MolmoPoint-8B-mxfp8

from Qwen/Qwen3-8B
MXFP8
Vision + text · Qwen ↓ 34 · ♥ 0
Params
8.7B
Weights
≈ 10.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

Nanonets-OCR-s-4bit

from Qwen/Qwen2.5-VL-3B-Instruct
4-bit
Vision + text · Qwen ↓ 33 · ♥ 0
Params
3.8B
Weights
≈ 3.1 GB
Mac memory
8 GB+

updated 2025-07-25

UGround-V1-2B

from Qwen/Qwen2-VL-2B
Vision + text · Qwen ↓ 32 · ♥ 0
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-04

olmOCR-7B-0725-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 31 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-07-25

Holo1-3B-8bit

from Qwen/Qwen2.5-VL-3B-Instruct
8-bit
Vision + text · Qwen ↓ 30 · ♥ 0
Params
3.8B
Weights
≈ 4.6 GB
Mac memory
8 GB+

other · updated 2025-06-03

Holo1-7B-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 27 · ♥ 2
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-03

Holo1-3B-6bit

from Qwen/Qwen2.5-VL-3B-Instruct
6-bit
Vision + text · Qwen ↓ 27 · ♥ 0
Params
3.8B
Weights
≈ 3.8 GB
Mac memory
8 GB+

other · updated 2025-06-03