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 7 of 18 · clear filters

diffusiongemma-26B-A4B-it-5bit

from google/diffusiongemma-26B-A4B-it
5-bit
Vision + text · Google · Gemma ↓ 168 · ♥ 2
Params
26B
Weights
≈ 18.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-15

ThinkingCap-Qwen3.6-27B-mlx-6Bit

from bottlecapai/ThinkingCap-Qwen3.6-27B
6-bit
Vision + text · bottlecapai ↓ 166 · ♥ 7
Params
27B
Weights
≈ 21.9 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-17

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

chartreader-0.8B-OptiQ-4bit

from mlx-community/Qwen3.5-0.8B-OptiQ-4bit
4-bit
Vision + text ↓ 163 · ♥ 2
Params
752M
Weights
≈ 424 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-30

dots.ocr-4bit

mlx-community/dots.ocr-4bit
4-bit
Vision + text ↓ 163 · ♥ 0
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

mit · updated 2026-02-16

gemma-3n-E4B-it-bf16

from google/gemma-3n-E4B
bf16
Vision + text · Google · Gemma ↓ 161 · ♥ 12
Params
8.4B
Weights
≈ 15.7 GB
Mac memory
24 GB+

gemma · updated 2025-07-12

dots.mocr-bf16

from rednote-hilab/dots.mocr
bf16
Vision + text · rednote-hilab ↓ 160 · ♥ 4
Params
3.0B
Weights
≈ 6.1 GB
Mac memory
16 GB+

mit · updated 2026-04-03

Fara1.5-9B-OptiQ-4bit

from microsoft/Fara1.5-9B
4-bit
Vision + text · Microsoft · Phi ↓ 160 · ♥ 3
Params
9.0B
Weights
≈ 6.0 GB
Mac memory
16 GB+

mit · updated 2026-10-18

NVIDIA-Nemotron-3-Nano-Omni-30B-A3B-4bit

from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
4-bit
Vision + text · NVIDIA ↓ 159 · ♥ 0
Params
33B
Weights
≈ 20.7 GB
Mac memory
32 GB+

nvidia-open-model-license · updated 2026-06-09

gemma-4-e2b-it-5bit

from google/gemma-4-E2B-it
5-bit
Vision + text · Google · Gemma ↓ 158 · ♥ 1
Params
5.1B
Weights
≈ 4.1 GB
Mac memory
8 GB+

gemma · updated 2026-07-06

Qwen3.5-27B-heretic-8bit

from coder3101/Qwen3.5-27B-heretic
8-bit
Vision + text · coder3101 ↓ 157 · ♥ 8
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-02-26

Qwen3.5-35B-A3B-6bit

mlx-community/Qwen3.5-35B-A3B-6bit
6-bit
Vision + text ↓ 157 · ♥ 2
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-02-24

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

medgemma-27b-it-4bit

from google/gemma-3-27b-pt
4-bit
Vision + text · Google · Gemma ↓ 155 · ♥ 3
Params
—
Weights
—
Mac memory
—

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

Qwopus3.8-27B-Flash-mxfp8-MLX

from Jackrong/Qwopus3.8-27B-Flash
MXFP8
Vision + text · Jackrong ↓ 153 · ♥ 0
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-09-14

diffusiongemma-26B-A4B-it-mxfp4

from google/diffusiongemma-26B-A4B-it
MXFP4
Vision + text · Google · Gemma ↓ 152 · ♥ 6
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-15

gemma-4-26B-A4B-it-qat-nvfp4

mlx-community/gemma-4-26B-A4B-it-qat-nvfp4
4-bit
Vision + text ↓ 152 · ♥ 3
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

updated 2026-06-05

Kestrel-4B-Coder-8bit

from unsloth/Qwen3.5-4B
8-bit
Vision + text · unsloth ↓ 152 · ♥ 0
Params
4.5B
Weights
≈ 5.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-07

Qwopus3.8-27B-Flash-V2-bf16

from Jackrong/Qwopus3.8-27B-Flash-V2
bf16
Vision + text · Jackrong ↓ 152 · ♥ 0
Params
27B
Weights
≈ 54.7 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-09-22

dots.mocr-4bit

from dots-studio/dots.mocr
4-bit
Vision + text · dots-studio ↓ 152 · ♥ 0
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

mit · updated 2026-04-03

LocateAnything-3B-4bit

from nvidia/LocateAnything-3B
4-bit
Vision + text · NVIDIA ↓ 151 · ♥ 20
Params
3.5B
Weights
≈ 2.6 GB
Mac memory
8 GB+

nvidia-license · updated 2026-05-29

DeepSeek-OCR-2-6bit

mlx-community/DeepSeek-OCR-2-6bit
6-bit
Vision + text ↓ 151 · ♥ 1
Params
3.4B
Weights
≈ 3.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-28

Florence-2-base-ft-4bit

mlx-community/Florence-2-base-ft-4bit
4-bit
Vision + text ↓ 150 · ♥ 1
Params
271M
Weights
≈ 163 MB
Mac memory
8 GB+

mit · updated 2024-11-21

deepseek-vl2-tiny-4bit

mlx-community/deepseek-vl2-tiny-4bit
4-bit
Vision + text ↓ 150 · ♥ 1
Params
3.4B
Weights
≈ 2.1 GB
Mac memory
8 GB+

deepseek · updated 2024-12-22

Kestrel-4B-Coder-4bit

from unsloth/Qwen3.5-4B
4-bit
Vision + text · unsloth ↓ 150 · ♥ 0
Params
4.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-11-07

Kimi-VL-A3B-Thinking-2506-5bit

from moonshotai/Kimi-VL-A3B-Instruct
5-bit
Vision + text · Moonshot · Kimi ↓ 150 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2026-01-27

Kimi-VL-A3B-Thinking-2506-bf16

from moonshotai/Kimi-VL-A3B-Instruct
bf16
Vision + text · Moonshot · Kimi ↓ 148 · ♥ 1
Params
16B
Weights
≈ 32.8 GB
Mac memory
48 GB+

mit · updated 2026-01-27

Kimi-VL-A3B-Thinking-6bit

from OpenGVLab/InternVL3-1B-Instruct
6-bit
Vision + text · OpenGVLab ↓ 147 · ♥ 1
Params
—
Weights
—
Mac memory
—

qwen · updated 2026-01-27

pixtral-12b-8bit

mlx-community/pixtral-12b-8bit
8-bit
Vision + text ↓ 145 · ♥ 8
Params
13B
Weights
≈ 13.5 GB
Mac memory
24 GB+

updated 2024-09-30

medgemma-4b-it-4bit

from google/medgemma-4b-pt
4-bit
Vision + text · Google · Gemma ↓ 145 · ♥ 3
Params
5.0B
Weights
≈ 3.0 GB
Mac memory
8 GB+

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

UI-TARS-1.5-7B-8bit

from ByteDance-Seed/UI-TARS-1.5-7B
8-bit
Vision + text · ByteDance-Seed ↓ 145 · ♥ 0
Params
8.3B
Weights
≈ 9.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-05-31

gemma-4-e2b-it-mxfp8

from google/gemma-4-E2B-it
MXFP8
Vision + text · Google · Gemma ↓ 144 · ♥ 0
Params
5.1B
Weights
≈ 5.9 GB
Mac memory
16 GB+

gemma · updated 2026-07-06

Nemotron-Parse-v1.2-8bit

from nvidia/NVIDIA-Nemotron-Parse-v1.2
8-bit
Vision + text · NVIDIA ↓ 143 · ♥ 0
Params
936M
Weights
≈ 1.6 GB
Mac memory
8 GB+

nvidia-open-model-license · updated 2026-08-13

Qwen2.5-VL-32B-Instruct-8bit

mlx-community/Qwen2.5-VL-32B-Instruct-8bit
8-bit
Vision + text ↓ 142 · ♥ 4
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-03-27

Llama-4-Maverick-17B-128E-Instruct-4bit

from meta-llama/Llama-4-Maverick-17B-128E
4-bit
Vision + text · Meta · Llama ↓ 142 · ♥ 2
Params
—
Weights
—
Mac memory
—

llama4 · updated 2025-04-07

diffusiongemma-26B-A4B-it-6bit

from google/diffusiongemma-26B-A4B-it
6-bit
Vision + text · Google · Gemma ↓ 141 · ♥ 4
Params
26B
Weights
≈ 21.7 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-15

DeepSeek-V4-Pro-Qwen3.5-4B-8bit

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B
8-bit
Vision + text · Jackrong ↓ 141 · ♥ 0
Params
4.5B
Weights
≈ 5.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-07

Muse-Glimmer-30B-mxfp8

from meta-models/Muse-Glimmer-30B
MXFP8
Vision + text · meta-models ↓ 141 · ♥ 0
Params
30B
Weights
≈ 33.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-08-11

Qwopus3.8-27B-Flash-mxfp4-MLX

from Jackrong/Qwopus3.8-27B-Flash
MXFP4
Vision + text · Jackrong ↓ 141 · ♥ 0
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-09-14

gemma-4-e2b-it-nvfp4

from google/gemma-4-E2B-it
4-bit
Vision + text · Google · Gemma ↓ 140 · ♥ 1
Params
5.1B
Weights
≈ 3.6 GB
Mac memory
8 GB+

gemma · updated 2026-07-06

deepseek-vl-1.3b-chat-4bit

mlx-community/deepseek-vl-1.3b-chat-4bit
4-bit
Vision + text ↓ 139 · ♥ 4
Params
2.0B
Weights
≈ 1.1 GB
Mac memory
8 GB+

deepseek · updated 2024-12-26

deepseek-vl2-4bit

mlx-community/deepseek-vl2-4bit
4-bit
Vision + text ↓ 139 · ♥ 2
Params
27B
Weights
≈ 15.7 GB
Mac memory
24 GB+

deepseek · updated 2024-12-22

LightOnOCR-2-1B-4bit

mlx-community/LightOnOCR-2-1B-4bit
4-bit
Vision + text ↓ 137 · ♥ 1
Params
1.0B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-06

deepseek-vl-7b-chat-4bit

mlx-community/deepseek-vl-7b-chat-4bit
4-bit
Vision + text ↓ 136 · ♥ 2
Params
7.3B
Weights
≈ 4.2 GB
Mac memory
8 GB+

deepseek · updated 2024-12-26

gemma-4-31B-it-qat-6bit

mlx-community/gemma-4-31B-it-qat-6bit
6-bit
Vision + text ↓ 136 · ♥ 1
Params
31B
Weights
≈ 26.1 GB
Mac memory
32 GB+

updated 2026-06-05

gemma-4-26b-a4b-it-mxfp8

from google/gemma-4-26B-A4B-it
MXFP8
Vision + text · Google · Gemma ↓ 135 · ♥ 4
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-05

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

GLM-4.6V-4bit

mlx-community/GLM-4.6V-4bit
4-bit
Vision + text ↓ 134 · ♥ 5
Params
—
Weights
—
Mac memory
—

mit · updated 2025-12-08

typhoon-ocr1.5-2b-8bit

from typhoon-ai/typhoon-ocr1.5-2b
8-bit
Vision + text · typhoon-ai ↓ 133 · ♥ 0
Params
2.1B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-26

Mage-VL-OptiQ-4bit

from microsoft/Mage-VL
4-bit
Vision + text · Microsoft · Phi ↓ 132 · ♥ 3
Params
4.4B
Weights
≈ 2.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-09-15

DeepSeek-OCR-bf16

mlx-community/DeepSeek-OCR-bf16
bf16
Vision + text ↓ 131 · ♥ 2
Params
3.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

mit · updated 2026-01-28

deepseek-vl2-small-4bit

mlx-community/deepseek-vl2-small-4bit
4-bit
Vision + text ↓ 131 · ♥ 0
Params
16B
Weights
≈ 9.3 GB
Mac memory
16 GB+

deepseek · updated 2024-12-22

Fara1.5-4B-OptiQ-4bit

from microsoft/Fara1.5-4B
4-bit
Vision + text · Microsoft · Phi ↓ 130 · ♥ 2
Params
4.2B
Weights
≈ 2.4 GB
Mac memory
8 GB+

mit · updated 2026-10-18

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-VL-2B-Instruct-bf16

mlx-community/Qwen3-VL-2B-Instruct-bf16
bf16
Vision + text ↓ 129 · ♥ 0
Params
2.1B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

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

Ministral-3-14B-Base-2512-4bit

from mistralai/Ministral-3-14B-Base-2512
4-bit
Vision + text · Mistral ↓ 125 · ♥ 1
Params
14B
Weights
≈ 9.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-07-18

Qwen3-VL-30B-A3B-Instruct-3bit

mlx-community/Qwen3-VL-30B-A3B-Instruct-3bit
3-bit
Vision + text ↓ 124 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-11