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 8 of 18 · clear filters

Llama-4-Scout-17B-16E-4bit

mlx-community/Llama-4-Scout-17B-16E-4bit
4-bit
Vision + text ↓ 122 · ♥ 2
Params
—
Weights
—
Mac memory
—

llama4 · updated 2025-04-06

chandra-4bit

mlx-community/chandra-4bit
4-bit
Vision + text ↓ 121 · ♥ 5
Params
—
Weights
—
Mac memory
—

openrail · updated 2025-10-21

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

InternVL3-2B-4bit

from OpenGVLab/InternViT-300M-448px-V2_5
4-bit
Vision + text · OpenGVLab ↓ 121 · ♥ 0
Params
2.1B
Weights
≈ 1.6 GB
Mac memory
8 GB+

qwen · updated 2025-04-14

Ornith-1.0-35B-OptiQ-4bit

from ornith-ai/Ornith-1.0-35B
4-bit
Vision + text · ornith-ai ↓ 119 · ♥ 3
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

mit · updated 2026-09-15

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

from Jackrong/Qwopus3.6-35B-A3B-Coder
6-bit
Vision + text · Jackrong ↓ 119 · ♥ 3
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-06-30

GLM-4.5V-abliterated-8bit

from zai-org/GLM-4.5V
8-bit
Vision + text · zai-org ↓ 119 · ♥ 1
Params
—
Weights
—
Mac memory
—

mit · updated 2025-09-05

granite-4.0-3b-vision-4bit

from ibm-granite/granite-4.0-3b-vision
4-bit
Vision + text · IBM · Granite ↓ 117 · ♥ 0
Params
4.3B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-01

paligemma-3b-mix-448-8bit

mlx-community/paligemma-3b-mix-448-8bit
8-bit
Vision + text ↓ 115 · ♥ 7
Params
2.9B
Weights
≈ 3.1 GB
Mac memory
8 GB+

gemma · updated 2024-10-18

gemma-3-4b-pt-4bit

mlx-community/gemma-3-4b-pt-4bit
4-bit
Vision + text ↓ 114 · ♥ 4
Params
5.0B
Weights
≈ 3.4 GB
Mac memory
8 GB+

gemma · updated 2025-03-18

DeepSeek-V4-Pro-Qwen3.5-4B-6bit

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B
6-bit
Vision + text · Jackrong ↓ 114 · ♥ 0
Params
4.5B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-07

Agents-A1-8bit

from InternScience/Agents-A1
8-bit
Vision + text · InternScience ↓ 113 · ♥ 4
Params
35B
Weights
≈ 37.7 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-01

dots.ocr-bf16

mlx-community/dots.ocr-bf16
bf16
Vision + text ↓ 113 · ♥ 4
Params
3.0B
Weights
≈ 6.1 GB
Mac memory
16 GB+

mit · updated 2026-02-17

GLM-4.1V-9B-Thinking-8bit

from zai-org/GLM-4.1V-9B-Thinking
8-bit
Vision + text · zai-org ↓ 113 · ♥ 3
Params
10B
Weights
≈ 11.8 GB
Mac memory
16 GB+

mit · updated 2026-07-31

Florence-2-base-ft-bf16

mlx-community/Florence-2-base-ft-bf16
bf16
Vision + text ↓ 112 · ♥ 1
Params
271M
Weights
≈ 542 MB
Mac memory
8 GB+

mit · updated 2024-11-21

Florence-2-large-ft-bf16

mlx-community/Florence-2-large-ft-bf16
bf16
Vision + text ↓ 112 · ♥ 1
Params
823M
Weights
≈ 1.6 GB
Mac memory
8 GB+

mit · updated 2024-11-21

DeepSeek-V4-Pro-Qwen3.5-4B-bf16

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B
bf16
Vision + text · Jackrong ↓ 112 · ♥ 0
Params
4.5B
Weights
≈ 9.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-07

Agents-A1-OptiQ-4bit

from InternScience/Agents-A1
4-bit
Vision + text · InternScience ↓ 111 · ♥ 3
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-09-15

Qwopus3.6-35B-A3B-Coder-4bit

from Jackrong/Qwopus3.6-35B-A3B-Coder
4-bit
Vision + text · Jackrong ↓ 111 · ♥ 3
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-06-30

gemma-4-26B-A4B-it-qat-bf16

mlx-community/gemma-4-26B-A4B-it-qat-bf16
bf16
Vision + text ↓ 111 · ♥ 2
Params
26B
Weights
≈ 51.6 GB
Mac memory
64 GB+

updated 2026-06-05

gemma-3-27b-it-8bit

from google/gemma-3-27b-pt
8-bit
Vision + text · Google · Gemma ↓ 110 · ♥ 7
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-04-03

GLM-4.6V-mxfp4

from zai-org/GLM-4.6V
MXFP4
Vision + text · zai-org ↓ 110 · ♥ 4
Params
108B
Weights
≈ 61.9 GB
Mac memory
96 GB+

mit · updated 2026-02-21

LFM2.5-VL-1.6B-8bit

from LiquidAI/LFM2.5-1.2B-Base
8-bit
Vision + text · LiquidAI ↓ 110 · ♥ 2
Params
1.6B
Weights
≈ 2.1 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

Inkling-Small-mlx-3bit

from thinkingmachines/Inkling-Small
3-bit
Vision + text · thinkingmachines ↓ 109 · ♥ 1
Params
264B
Weights
≈ 121 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-07-31

SmolVLM-500M-Instruct-bf16

from HuggingFaceTB/SmolLM2-360M-Instruct
bf16
Vision + text · Hugging Face ↓ 109 · ♥ 1
Params
507M
Weights
≈ 1.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-23

LightOnOCR-2-1B-8bit

mlx-community/LightOnOCR-2-1B-8bit
8-bit
Vision + text ↓ 108 · ♥ 2
Params
1.0B
Weights
≈ 1.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-06

LocateAnything-3B-bf16

from nvidia/LocateAnything-3B
bf16
Vision + text · NVIDIA ↓ 108 · ♥ 2
Params
3.5B
Weights
≈ 7.0 GB
Mac memory
16 GB+

nvidia-license · updated 2026-05-29

PaddleOCR-VL-bfloat16

from baidu/ERNIE-4.5-0.3B-Paddle
Vision + text · baidu ↓ 108 · ♥ 1
Params
906M
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-19

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

gemma-4-26b-a4b-8bit

from google/gemma-4-26b-a4b
8-bit
Vision + text · Google · Gemma ↓ 107 · ♥ 7
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-03

Ministral-3-8B-Base-2512-4bit

from mistralai/Ministral-3-8B-Base-2512
4-bit
Vision + text · Mistral ↓ 107 · ♥ 0
Params
8.5B
Weights
≈ 4.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-18

InternVL3-1B-4bit

from OpenGVLab/InternViT-300M-448px-V2_5
4-bit
Vision + text · OpenGVLab ↓ 106 · ♥ 0
Params
938M
Weights
≈ 965 MB
Mac memory
8 GB+

qwen · updated 2025-04-14

Qwen2.5-VL-32B-Instruct-6bit

mlx-community/Qwen2.5-VL-32B-Instruct-6bit
6-bit
Vision + text ↓ 105 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-03-26

gemma-4-26b-a4b-bf16

from google/gemma-4-26b-a4b
bf16
Vision + text · Google · Gemma ↓ 104 · ♥ 5
Params
26B
Weights
≈ 51.6 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-04-03

InternVL3_5-GPT-OSS-20B-A4B-Preview-4bit

from OpenGVLab/InternViT-300M-448px-V2_5
4-bit
Vision + text · OpenGVLab ↓ 104 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-04

MAI-UI-2B-6bit-v2

from Tongyi-MAI/MAI-UI-2B
6-bit
Vision + text · Tongyi-MAI ↓ 103 · ♥ 1
Params
2.1B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-21

North-Mini-Code-1.0-6bit

from CohereLabs/North-Mini-Code-1.0
6-bit
Vision + text · Cohere ↓ 102 · ♥ 3
Params
30B
Weights
≈ 25.9 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-06-11

InternVL3-8B-6bit

from OpenGVLab/InternVL3-1B-Instruct
6-bit
Vision + text · OpenGVLab ↓ 102 · ♥ 1
Params
—
Weights
—
Mac memory
—

qwen · updated 2025-04-18

Ministral-3-14B-Base-2512-8bit

from mistralai/Ministral-3-14B-Base-2512
8-bit
Vision + text · Mistral ↓ 101 · ♥ 1
Params
14B
Weights
≈ 15.9 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-18

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

SmolVLM-256M-Instruct-8bit

from HuggingFaceTB/SmolLM2-135M-Instruct
8-bit
Vision + text · Hugging Face ↓ 101 · ♥ 0
Params
256M
Weights
≈ 273 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-23

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

Qwen3-VL-8B-Thinking-4bit

mlx-community/Qwen3-VL-8B-Thinking-4bit
4-bit
Vision + text ↓ 100 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

Qwen3-VL-30B-A3B-Instruct-bf16

mlx-community/Qwen3-VL-30B-A3B-Instruct-bf16
bf16
Vision + text ↓ 99 · ♥ 4
Params
31B
Weights
≈ 62.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-10-13

Qwen3-VL-30B-A3B-Instruct-6bit

mlx-community/Qwen3-VL-30B-A3B-Instruct-6bit
6-bit
Vision + text ↓ 99 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-11

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

llm-jp-4-vl-9b-mlx-4bit

from llm-jp/llm-jp-4-vl-9b
4-bit
Vision + text · llm-jp ↓ 99 · ♥ 0
Params
9.0B
Weights
≈ 5.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-09-09

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

gemma-4-31B-it-qat-5bit

mlx-community/gemma-4-31B-it-qat-5bit
5-bit
Vision + text ↓ 97 · ♥ 1
Params
31B
Weights
≈ 22.2 GB
Mac memory
32 GB+

updated 2026-06-05

MinerU2.5-2509-1.2B-bf16

mlx-community/MinerU2.5-2509-1.2B-bf16
bf16
Vision + text ↓ 97 · ♥ 0
Params
1.2B
Weights
≈ 2.3 GB
Mac memory
8 GB+

agpl-3.0 · updated 2025-10-04

deepseek-vl-1.3b-chat-8bit

mlx-community/deepseek-vl-1.3b-chat-8bit
8-bit
Vision + text ↓ 95 · ♥ 1
Params
2.0B
Weights
≈ 2.1 GB
Mac memory
8 GB+

deepseek · updated 2024-12-26

InternVL3_5-30B-A3B-4bit

from OpenGVLab/InternVL3_5-30B-A3B-MPO
4-bit
Vision + text · OpenGVLab ↓ 95 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-04

gemma-4-26b-a4b-mxfp4

from google/gemma-4-26b-a4b
MXFP4
Vision + text · Google · Gemma ↓ 94 · ♥ 8
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-03

gemma-4-e4b-it-5bit

from google/gemma-4-E4B-it
5-bit
Vision + text · Google · Gemma ↓ 94 · ♥ 1
Params
7.9B
Weights
≈ 6.1 GB
Mac memory
16 GB+

gemma · updated 2026-07-06

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