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 3 of 3 · clear filters

olmOCR-7B-0225-preview-6bit

from Qwen/Qwen2-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 27 · ♥ 0
Params
8.3B
Weights
≈ 7.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-03

QVQ-72B-Preview-8bit

from Qwen/Qwen2-VL-72B
8-bit
Vision + text · Qwen ↓ 25 · ♥ 3
Params
73B
Weights
≈ 78.0 GB
Mac memory
96 GB+

qwen · updated 2024-12-24

Holo1-3B-bf16

from Qwen/Qwen2.5-VL-3B-Instruct
bf16
Vision + text · Qwen ↓ 25 · ♥ 0
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

other · updated 2025-06-03

Holo1-7B-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 25 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-06-03

Holo1-7B-3bit

from Qwen/Qwen2.5-VL-7B-Instruct
3-bit
Vision + text · Qwen ↓ 24 · ♥ 0
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-03

Holo1-7B-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 24 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-06-03

olmOCR-7B-0725-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 24 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-24

Jedi-7B-1080p-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Vision + text · Qwen ↓ 23 · ♥ 1
Params
8.3B
Weights
≈ 4.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-01

X-Reasoner-7B-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 23 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-02-04

QVQ-72B-Preview-3bit

from Qwen/Qwen2-VL-72B
3-bit
Vision + text · Qwen ↓ 22 · ♥ 5
Params
73B
Weights
≈ 32.1 GB
Mac memory
48 GB+

qwen · updated 2024-12-24

Jedi-7B-1080p-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 21 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-06-01

Nanonets-OCR-s-8bit

from Qwen/Qwen2.5-VL-3B-Instruct
8-bit
Vision + text · Qwen ↓ 21 · ♥ 0
Params
3.8B
Weights
≈ 4.6 GB
Mac memory
8 GB+

updated 2025-07-25

QVQ-72B-Preview-bf16

from Qwen/Qwen2-VL-72B
bf16
Vision + text · Qwen ↓ 20 · ♥ 3
Params
73B
Weights
≈ 147 GB
Mac memory
192 GB+

qwen · updated 2024-12-24

QVQ-72B-Preview-6bit

from Qwen/Qwen2-VL-72B
6-bit
Vision + text · Qwen ↓ 20 · ♥ 2
Params
73B
Weights
≈ 59.6 GB
Mac memory
96 GB+

qwen · updated 2024-12-24

EvoCUA-8B-20260105-8bit

from Qwen/Qwen3-VL-32B
8-bit
Vision + text · Qwen ↓ 20 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-01-26

olmOCR-7B-0725-6bit

from Qwen/Qwen2.5-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 20 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-07-25

Nanonets-OCR-s-6bit

from Qwen/Qwen2.5-VL-3B-Instruct
6-bit
Vision + text · Qwen ↓ 19 · ♥ 0
Params
3.8B
Weights
≈ 3.8 GB
Mac memory
8 GB+

updated 2025-07-25

Jedi-7B-1080p-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 16 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-01

Jedi-7B-1080p-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 13 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-06-01