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

1,022 builds · page 9 of 18 · clear filters

GLM-4.6V-Flash-mxfp4

from zai-org/GLM-4.6V-Flash
MXFP4
Vision + text · zai-org ↓ 93 · ♥ 3
Params
10B
Weights
≈ 7.1 GB
Mac memory
16 GB+

mit · updated 2026-02-21

Qwen3.5-27B-6bit

mlx-community/Qwen3.5-27B-6bit
6-bit
Vision + text ↓ 92 · ♥ 3
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-02-24

GLM-4.6V-Flash-8bit

mlx-community/GLM-4.6V-Flash-8bit
8-bit
Vision + text ↓ 92 · ♥ 2
Params
—
Weights
—
Mac memory
—

mit · updated 2025-12-08

deepseek-vl2-6bit

mlx-community/deepseek-vl2-6bit
6-bit
Vision + text ↓ 92 · ♥ 1
Params
27B
Weights
≈ 22.5 GB
Mac memory
32 GB+

deepseek · updated 2024-12-22

deepseek-vl2-tiny-8bit

mlx-community/deepseek-vl2-tiny-8bit
8-bit
Vision + text ↓ 92 · ♥ 0
Params
3.4B
Weights
≈ 3.7 GB
Mac memory
8 GB+

deepseek · updated 2024-12-22

Qwen3-VL-8B-Instruct-6bit

mlx-community/Qwen3-VL-8B-Instruct-6bit
6-bit
Vision + text ↓ 91 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

diffusiongemma-26B-A4B-it-bf16

from google/diffusiongemma-26B-A4B-it
bf16
Vision + text · Google · Gemma ↓ 91 · ♥ 2
Params
26B
Weights
≈ 51.6 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-07-15

deepseek-vl2-tiny-6bit

mlx-community/deepseek-vl2-tiny-6bit
6-bit
Vision + text ↓ 91 · ♥ 1
Params
3.4B
Weights
≈ 2.9 GB
Mac memory
8 GB+

deepseek · updated 2024-12-22

Ministral-3-3B-Base-2512-8bit

from mistralai/Ministral-3-3B-Base-2512
8-bit
Vision + text · Mistral ↓ 91 · ♥ 0
Params
3.8B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-18

Qwen3-VL-4B-Thinking-4bit

mlx-community/Qwen3-VL-4B-Thinking-4bit
4-bit
Vision + text ↓ 91 · ♥ 0
Params
4.4B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

Agents-A1-6bit

from InternScience/Agents-A1
6-bit
Vision + text · InternScience ↓ 90 · ♥ 4
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-01

Ornith-1.0-35B-OptiQ-6bit

from ornith-ai/Ornith-1.0-35B
6-bit
Vision + text · ornith-ai ↓ 90 · ♥ 3
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

mit · updated 2026-09-15

MiMo-VL-7B-RL-4bit

from XiaomiMiMo/MiMo-VL-7B-RL
4-bit
Vision + text · XiaomiMiMo ↓ 90 · ♥ 0
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

mit · updated 2025-05-31

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

Ornith-1.0-35B-8bit

from ornith-ai/Ornith-1.0-35B
8-bit
Vision + text · ornith-ai ↓ 88 · ♥ 9
Params
35B
Weights
≈ 37.7 GB
Mac memory
48 GB+

mit · updated 2026-06-27

Qwen2-VL-72B-Instruct-4bit

mlx-community/Qwen2-VL-72B-Instruct-4bit
4-bit
Vision + text ↓ 88 · ♥ 5
Params
73B
Weights
≈ 41.3 GB
Mac memory
64 GB+

tongyi-qianwen · updated 2025-03-24

gemma-4-E4B-it-qat-6bit

mlx-community/gemma-4-E4B-it-qat-6bit
6-bit
Vision + text ↓ 88 · ♥ 1
Params
7.9B
Weights
≈ 7.0 GB
Mac memory
16 GB+

updated 2026-06-05

medgemma-4b-it-8bit

from google/medgemma-4b-pt
8-bit
Vision + text · Google · Gemma ↓ 87 · ♥ 3
Params
4.6B
Weights
≈ 4.8 GB
Mac memory
8 GB+

health-ai-developer-foundations · updated 2025-06-09

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

MiMo-VL-7B-RL-8bit

from XiaomiMiMo/MiMo-VL-7B-RL
8-bit
Vision + text · XiaomiMiMo ↓ 86 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-05-31

gemma-3-4b-pt-bf16

mlx-community/gemma-3-4b-pt-bf16
bf16
Vision + text ↓ 85 · ♥ 2
Params
5.0B
Weights
≈ 9.9 GB
Mac memory
16 GB+

gemma · updated 2025-03-18

InternVL3-8B-8bit

from OpenGVLab/InternVL3-1B-Instruct
8-bit
Vision + text · OpenGVLab ↓ 85 · ♥ 0
Params
—
Weights
—
Mac memory
—

qwen · updated 2025-04-18

Ministral-3-14B-Base-2512-6bit

from mistralai/Ministral-3-14B-Base-2512
6-bit
Vision + text · Mistral ↓ 85 · ♥ 0
Params
14B
Weights
≈ 12.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-18

command-a-vision-07-2025-4bit

from CohereLabs/c4ai-command-a-03-2025
4-bit
Vision + text · Cohere ↓ 85 · ♥ 0
Params
—
Weights
—
Mac memory
—

cc-by-nc-4.0 · updated 2025-08-19

Qwopus3.6-35B-A3B-Coder-8bit

from Jackrong/Qwopus3.6-35B-A3B-Coder
8-bit
Vision + text · Jackrong ↓ 84 · ♥ 4
Params
35B
Weights
≈ 37.7 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-06-30

CodeFormulaV2-mlx-bf16

from docling-project/CodeFormulaV2
bf16
Vision + text · docling-project ↓ 84 · ♥ 1
Params
315M
Weights
≈ 631 MB
Mac memory
8 GB+

cdla-permissive-2.0 · updated 2026-05-16

GLM-4.1V-9B-Thinking-4bit

from zai-org/GLM-4-9B-0414
4-bit
Vision + text · zai-org ↓ 84 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-11-10

deepseek-vl2-small-bf16

mlx-community/deepseek-vl2-small-bf16
bf16
Vision + text ↓ 83 · ♥ 0
Params
16B
Weights
≈ 32.3 GB
Mac memory
48 GB+

deepseek · updated 2024-12-22

Ministral-3-14B-Base-2512-bf16

from mistralai/Ministral-3-14B-Base-2512
bf16
Vision + text · Mistral ↓ 82 · ♥ 1
Params
14B
Weights
≈ 27.9 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-18

Qwen2-VL-2B-Instruct-bf16

mlx-community/Qwen2-VL-2B-Instruct-bf16
bf16
Vision + text ↓ 82 · ♥ 1
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-24

DeepSeek-OCR-6bit

mlx-community/DeepSeek-OCR-6bit
6-bit
Vision + text ↓ 81 · ♥ 2
Params
3.3B
Weights
≈ 3.2 GB
Mac memory
8 GB+

mit · updated 2026-01-28

InternVL3-14B-4bit

from OpenGVLab/InternVL3-1B-Instruct
4-bit
Vision + text · OpenGVLab ↓ 81 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

chandra-8bit

mlx-community/chandra-8bit
8-bit
Vision + text ↓ 80 · ♥ 2
Params
—
Weights
—
Mac memory
—

openrail · updated 2025-10-21

gemma-3-27b-it-qat-8bit

from OpenGVLab/InternVL3-1B-Instruct
8-bit
Vision + text · OpenGVLab ↓ 79 · ♥ 9
Params
—
Weights
—
Mac memory
—

qwen · updated 2025-04-19

Qwen2-VL-7B-Instruct-bf16

mlx-community/Qwen2-VL-7B-Instruct-bf16
bf16
Vision + text ↓ 79 · ♥ 4
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-24

Huihui-GLM-4.5V-abliterated-5bit

from zai-org/GLM-4.5V
5-bit
Vision + text · zai-org ↓ 79 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-09-04

deepseek-vl2-tiny-bf16

mlx-community/deepseek-vl2-tiny-bf16
bf16
Vision + text ↓ 79 · ♥ 0
Params
3.4B
Weights
≈ 6.7 GB
Mac memory
16 GB+

deepseek · updated 2024-12-22

Ornith-1.0-9B-OptiQ-6bit

from ornith-ai/Ornith-1.0-9B
6-bit
Vision + text · ornith-ai ↓ 78 · ♥ 3
Params
9.0B
Weights
≈ 7.3 GB
Mac memory
16 GB+

mit · updated 2026-08-07

Florence-2-large-ft-8bit

mlx-community/Florence-2-large-ft-8bit
8-bit
Vision + text ↓ 78 · ♥ 1
Params
823M
Weights
≈ 901 MB
Mac memory
8 GB+

mit · updated 2024-11-21

huihui-Qwen3-VL-2B-Instruct-ab-4bit

from huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated
4-bit
Vision + text · huihui-ai ↓ 78 · ♥ 1
Params
2.1B
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-20

gemma-3-12b-it-6bit

from google/gemma-3-12b-pt
6-bit
Vision + text · Google · Gemma ↓ 78 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-03-19

diffusiongemma-26B-A4B-it-mxfp8

from google/diffusiongemma-26B-A4B-it
MXFP8
Vision + text · Google · Gemma ↓ 77 · ♥ 3
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-15

GLM-4.5V-abliterated-4bit

from zai-org/GLM-4.5V
4-bit
Vision + text · zai-org ↓ 77 · ♥ 1
Params
—
Weights
—
Mac memory
—

mit · updated 2025-09-05

MiMo-VL-7B-RL-bf16

from XiaomiMiMo/MiMo-VL-7B-RL
bf16
Vision + text · XiaomiMiMo ↓ 77 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

mit · updated 2025-05-31

Qwen3-VL-8B-Instruct-3bit

mlx-community/Qwen3-VL-8B-Instruct-3bit
3-bit
Vision + text ↓ 77 · ♥ 0
Params
8.8B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

deepseek-vl2-small-6bit

mlx-community/deepseek-vl2-small-6bit
6-bit
Vision + text ↓ 77 · ♥ 0
Params
16B
Weights
≈ 13.3 GB
Mac memory
24 GB+

deepseek · updated 2024-12-22

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

medgemma-27b-it-bf16

from google/gemma-3-27b-pt
bf16
Vision + text · Google · Gemma ↓ 76 · ♥ 3
Params
—
Weights
—
Mac memory
—

health-ai-developer-foundations · updated 2025-07-10

North-Micro-Vision-Instruct-4bit

from CohereLabs/North-Micro-Vision-Instruct
4-bit
Vision + text · Cohere ↓ 76 · ♥ 1
Params
2.5B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

deepseek-vl-7b-chat-8bit

mlx-community/deepseek-vl-7b-chat-8bit
8-bit
Vision + text ↓ 76 · ♥ 0
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+

deepseek · updated 2024-12-26

gemma-3n-E2B-it-bf16

from google/gemma-3n-E4B-it
bf16
Vision + text · Google · Gemma ↓ 76 · ♥ 0
Params
6.0B
Weights
≈ 10.9 GB
Mac memory
16 GB+

gemma · updated 2025-07-12

granite-vision-3.2-2b-4bit

from ibm-granite/granite-vision-3.2-2b
4-bit
Vision + text · IBM · Granite ↓ 75 · ♥ 0
Params
3.1B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-01

SmolVLM-Instruct-bf16

from HuggingFaceTB/SmolVLM-Instruct
bf16
Vision + text · Hugging Face ↓ 74 · ♥ 5
Params
2.2B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-11-29

GLM-4.6V-Flash-bf16

mlx-community/GLM-4.6V-Flash-bf16
bf16
Vision + text ↓ 74 · ♥ 4
Params
10B
Weights
≈ 20.6 GB
Mac memory
32 GB+

mit · updated 2025-12-08

OvisOCR2-4bit

from ATH-MaaS/OvisOCR2
4-bit
Vision + text · ATH-MaaS ↓ 74 · ♥ 0
Params
853M
Weights
≈ 625 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-04

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

OvisOCR2-6bit

from ATH-MaaS/OvisOCR2
6-bit
Vision + text · ATH-MaaS ↓ 73 · ♥ 1
Params
853M
Weights
≈ 813 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-04

gemma-4-26B-A4B-it-qat-mxfp8

mlx-community/gemma-4-26B-A4B-it-qat-mxfp8
MXFP8
Vision + text ↓ 72 · ♥ 2
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

updated 2026-06-05