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 2h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

1,022 builds · page 13 of 18 · clear filters

North-Micro-Vision-Instruct-bf16

from CohereLabs/North-Micro-Vision-Instruct
bf16
Vision + text · Cohere ↓ 43 · ♥ 0
Params
2.5B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Tess-4-27B-nvfp4

from migtissera/Tess-4-27B
4-bit
Vision + text · migtissera ↓ 43 · ♥ 0
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-10

granite-vision-3.2-2b-8bit

from ibm-granite/granite-vision-3.2-2b
8-bit
Vision + text · IBM · Granite ↓ 43 · ♥ 0
Params
3.1B
Weights
≈ 3.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-01

Lingshu-32B-4bit

mlx-community/Lingshu-32B-4bit
4-bit
Vision + text ↓ 42 · ♥ 2
Params
—
Weights
—
Mac memory
—

mit · updated 2025-06-12

ERNIE-4.5-VL-28B-A3B-Thinking-8bit

mlx-community/ERNIE-4.5-VL-28B-A3B-Thinking-8bit
8-bit
Vision + text ↓ 42 · ♥ 0
Params
29B
Weights
≈ 31.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-01-28

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

gemma-3n-E4B-4bit

mlx-community/gemma-3n-E4B-4bit
4-bit
Vision + text ↓ 42 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

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

Ornith-1.0-35B-5bit

from ornith-ai/Ornith-1.0-35B
5-bit
Vision + text · ornith-ai ↓ 41 · ♥ 1
Params
35B
Weights
≈ 24.7 GB
Mac memory
32 GB+

mit · updated 2026-06-27

Qwen2-VL-2B-8bit

mlx-community/Qwen2-VL-2B-8bit
8-bit
Vision + text ↓ 41 · ♥ 1
Params
2.2B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-24

ERNIE-4.5-VL-28B-A3B-Thinking-bf16

mlx-community/ERNIE-4.5-VL-28B-A3B-Thinking-bf16
bf16
Vision + text ↓ 41 · ♥ 0
Params
29B
Weights
≈ 58.8 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-01-28

GUI-Owl-7B-6bit

from mPLUG/GUI-Owl-7B
6-bit
Vision + text · mPLUG ↓ 41 · ♥ 0
Params
8.3B
Weights
≈ 7.6 GB
Mac memory
16 GB+

mit · updated 2026-03-20

Idefics3-8B-Llama3-4bit

mlx-community/Idefics3-8B-Llama3-4bit
4-bit
Vision + text ↓ 41 · ♥ 0
Params
8.5B
Weights
≈ 5.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-30

Qwen3-VL-2B-Instruct-3bit

mlx-community/Qwen3-VL-2B-Instruct-3bit
3-bit
Vision + text ↓ 41 · ♥ 0
Params
2.1B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

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

mlx-community/Qwen3-VL-30B-A3B-Thinking-6bit
6-bit
Vision + text ↓ 41 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

Qwen3-VL-30B-A3B-Thinking-8bit

mlx-community/Qwen3-VL-30B-A3B-Thinking-8bit
8-bit
Vision + text ↓ 41 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

gemma-4-E2B-it-qat-mxfp8

mlx-community/gemma-4-E2B-it-qat-mxfp8
MXFP8
Vision + text ↓ 41 · ♥ 0
Params
5.1B
Weights
≈ 5.9 GB
Mac memory
16 GB+

updated 2026-06-05

gemma-3-27b-it-qat-bf16

from google/gemma-3-27b-it
bf16
Vision + text · Google · Gemma ↓ 40 · ♥ 6
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-04-18

Qwen2-VL-7B-4bit

mlx-community/Qwen2-VL-7B-4bit
4-bit
Vision + text ↓ 40 · ♥ 3
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-24

gemma-3n-E2B-8bit

from google/gemma-3n-E4B
8-bit
Vision + text · Google · Gemma ↓ 40 · ♥ 2
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

gemma-4-26b-a4b-mxfp8

from google/gemma-4-26b-a4b
MXFP8
Vision + text · Google · Gemma ↓ 40 · ♥ 1
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-03

medgemma-4b-it-6bit

from google/medgemma-4b-pt
6-bit
Vision + text · Google · Gemma ↓ 40 · ♥ 1
Params
5.0B
Weights
≈ 4.2 GB
Mac memory
8 GB+

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

paligemma2-3b-ft-docci-448-bf16

mlx-community/paligemma2-3b-ft-docci-448-bf16
bf16
Vision + text ↓ 40 · ♥ 1
Params
3.0B
Weights
≈ 6.1 GB
Mac memory
16 GB+

gemma · updated 2024-12-05

Fara-7B-8bit

from microsoft/Fara-7B
8-bit
Vision + text · Microsoft · Phi ↓ 40 · ♥ 0
Params
8.3B
Weights
≈ 9.4 GB
Mac memory
16 GB+

mit · updated 2026-07-31

Idefics3-8B-Llama3-6bit

mlx-community/Idefics3-8B-Llama3-6bit
6-bit
Vision + text ↓ 40 · ♥ 0
Params
8.5B
Weights
≈ 7.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-01-30

North-Micro-Vision-Instruct-mxfp4

from CohereLabs/North-Micro-Vision-Instruct
MXFP4
Vision + text · Cohere ↓ 40 · ♥ 0
Params
2.5B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Qwopus3.6-27B-Coder-bf16

from Jackrong/Qwopus3.6-27B-Coder
bf16
Vision + text · Jackrong ↓ 40 · ♥ 0
Params
27B
Weights
≈ 54.7 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-07-01

UI-TARS-7B-SFT-8bit

mlx-community/UI-TARS-7B-SFT-8bit
8-bit
Vision + text ↓ 40 · ♥ 0
Params
8.3B
Weights
≈ 9.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-03

gemma-3n-E2B-it-8bit

from google/gemma-3n-E4B-it
8-bit
Vision + text · Google · Gemma ↓ 40 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

gemma-4-E2B-it-qat-6bit

mlx-community/gemma-4-E2B-it-qat-6bit
6-bit
Vision + text ↓ 40 · ♥ 0
Params
5.1B
Weights
≈ 4.7 GB
Mac memory
8 GB+

updated 2026-06-05

LFM2-VL-3B-8bit

mlx-community/LFM2-VL-3B-8bit
8-bit
Vision + text ↓ 39 · ♥ 4
Params
3.0B
Weights
≈ 3.6 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-15

Apriel-1.5-15b-Thinker-2bit-MLX

from ServiceNow-AI/Apriel-1.5-15b-Thinker
2-bit
Vision + text · ServiceNow-AI ↓ 39 · ♥ 1
Params
15B
Weights
≈ 5.3 GB
Mac memory
8 GB+

mit · updated 2025-10-03

Qwopus3.5-4B-v3-4bit

from Jackrong/Qwopus3.5-4B-v3
4-bit
Vision + text · Jackrong ↓ 39 · ♥ 1
Params
4.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-05

Ministral-3-8B-Base-2512-6bit

from mistralai/Ministral-3-8B-Base-2512
6-bit
Vision + text · Mistral ↓ 39 · ♥ 0
Params
8.9B
Weights
≈ 8.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-07-18

North-Micro-Vision-Instruct-mxfp8

from CohereLabs/North-Micro-Vision-Instruct
MXFP8
Vision + text · Cohere ↓ 39 · ♥ 0
Params
2.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

North-Micro-Vision-Instruct-nvfp4

from CohereLabs/North-Micro-Vision-Instruct
4-bit
Vision + text · Cohere ↓ 39 · ♥ 0
Params
2.5B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Qwen3-VL-2B-Instruct-5bit

mlx-community/Qwen3-VL-2B-Instruct-5bit
5-bit
Vision + text ↓ 39 · ♥ 0
Params
2.1B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

Qwen3-VL-32B-Thinking-bf16

mlx-community/Qwen3-VL-32B-Thinking-bf16
bf16
Vision + text ↓ 39 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

Qwen3.5-27B-heretic-v3-mxfp8

from llmfan46/Qwen3.5-27B-uncensored-heretic-v1
MXFP8
Vision + text · llmfan46 ↓ 39 · ♥ 0
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-03-28

dots.mocr-5bit

from dots-studio/dots.mocr
5-bit
Vision + text · dots-studio ↓ 39 · ♥ 0
Params
3.0B
Weights
≈ 3.7 GB
Mac memory
8 GB+

mit · updated 2026-04-03

dots.mocr-mxfp4

from dots-studio/dots.mocr
MXFP4
Vision + text · dots-studio ↓ 39 · ♥ 0
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

mit · updated 2026-04-03

ui-tars-7b-dpo

mlx-community/ui-tars-7b-dpo
Vision + text ↓ 39 · ♥ 0
Params
8.3B
Weights
≈ 33.2 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-02-11

LFM2-VL-450M-5bit

mlx-community/LFM2-VL-450M-5bit
5-bit
Vision + text ↓ 38 · ♥ 1
Params
451M
Weights
≈ 423 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-08-16

P1-VL-30B-A3B-bf16

from PRIME-RL/P1-VL-30B-A3B
bf16
Vision + text · PRIME-RL ↓ 38 · ♥ 1
Params
31B
Weights
≈ 62.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-05-18

Qwen3-VL-4B-Thinking-3bit

mlx-community/Qwen3-VL-4B-Thinking-3bit
3-bit
Vision + text ↓ 38 · ♥ 1
Params
4.4B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

aya-vision-32b-bf16

mlx-community/aya-vision-32b-bf16
bf16
Vision + text ↓ 38 · ♥ 1
Params
33B
Weights
≈ 66.3 GB
Mac memory
96 GB+

cc-by-nc-4.0 · updated 2025-03-05

ERNIE-4.5-VL-28B-A3B-Thinking-6bit

mlx-community/ERNIE-4.5-VL-28B-A3B-Thinking-6bit
6-bit
Vision + text ↓ 38 · ♥ 0
Params
29B
Weights
≈ 24.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-01-28

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

North-Micro-Vision-Instruct-6bit

from CohereLabs/North-Micro-Vision-Instruct
6-bit
Vision + text · Cohere ↓ 38 · ♥ 0
Params
2.5B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Qwen3-VL-30B-A3B-Thinking-5bit

mlx-community/Qwen3-VL-30B-A3B-Thinking-5bit
5-bit
Vision + text ↓ 38 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

chandra-6bit

mlx-community/chandra-6bit
6-bit
Vision + text ↓ 38 · ♥ 0
Params
—
Weights
—
Mac memory
—

openrail · updated 2025-10-21

chandra-bf16

mlx-community/chandra-bf16
bf16
Vision + text ↓ 38 · ♥ 0
Params
8.8B
Weights
≈ 17.5 GB
Mac memory
24 GB+

openrail · updated 2025-10-21

dots.ocr-mxfp8

mlx-community/dots.ocr-mxfp8
MXFP8
Vision + text ↓ 38 · ♥ 0
Params
3.0B
Weights
≈ 4.4 GB
Mac memory
8 GB+

mit · updated 2026-02-17

granite-vision-3.2-2b-6bit

from ibm-granite/granite-vision-3.2-2b
6-bit
Vision + text · IBM · Granite ↓ 38 · ♥ 0
Params
3.1B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-01

numind-NuExtract-2.0-8B-MLX

from numind/NuExtract-2.0-8B
Vision + text · numind ↓ 38 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

mit · updated 2026-04-14

llava-1.5-7b-8bit

mlx-community/llava-1.5-7b-8bit
8-bit
Vision + text ↓ 37 · ♥ 3
Params
7.1B
Weights
≈ 7.5 GB
Mac memory
16 GB+

llama2 · updated 2024-10-11

ShowUI-2B-6bit-v2

from showlab/ShowUI-2B
6-bit
Vision + text · showlab ↓ 37 · ♥ 1
Params
2.4B
Weights
≈ 2.8 GB
Mac memory
8 GB+

mit · updated 2026-03-20

gemma-4-E4B-it-qat-bf16

mlx-community/gemma-4-E4B-it-qat-bf16
bf16
Vision + text ↓ 37 · ♥ 1
Params
7.9B
Weights
≈ 15.9 GB
Mac memory
24 GB+

updated 2026-06-05

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-VL-2B-Thinking-8bit

mlx-community/Qwen3-VL-2B-Thinking-8bit
8-bit
Vision + text ↓ 37 · ♥ 0
Params
2.1B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21