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 16 of 18 · clear filters

Holo1-7B-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 27 · ♥ 2
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-03

LFM2-VL-450M-bf16

mlx-community/LFM2-VL-450M-bf16
bf16
Vision + text ↓ 27 · ♥ 1
Params
451M
Weights
≈ 902 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-08-16

Holo1-3B-6bit

from Qwen/Qwen2.5-VL-3B-Instruct
6-bit
Vision + text · Qwen ↓ 27 · ♥ 0
Params
3.8B
Weights
≈ 3.8 GB
Mac memory
8 GB+

other · updated 2025-06-03

Idefics3-8B-Llama3-3bit

mlx-community/Idefics3-8B-Llama3-3bit
3-bit
Vision + text ↓ 27 · ♥ 0
Params
8.5B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-30

InternVL3-14B-8bit

from OpenGVLab/InternVL3-1B-Instruct
8-bit
Vision + text · OpenGVLab ↓ 27 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

LFM2.5-VL-1.6B-5bit

from LiquidAI/LFM2.5-1.2B-Base
5-bit
Vision + text · LiquidAI ↓ 27 · ♥ 0
Params
1.6B
Weights
≈ 1.6 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

MAI-UI-8B-bf16

from Tongyi-MAI/MAI-UI-8B
bf16
Vision + text · Tongyi-MAI ↓ 27 · ♥ 0
Params
8.8B
Weights
≈ 17.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-03-20

Tess-4-27B-mxfp4

from migtissera/Tess-4-27B
MXFP4
Vision + text · migtissera ↓ 27 · ♥ 0
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-10

UI-TARS-72B-DPO-4bit

mlx-community/UI-TARS-72B-DPO-4bit
4-bit
Vision + text ↓ 27 · ♥ 0
Params
73B
Weights
≈ 42.3 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-03-06

UI-TARS-72B-SFT-4bit

mlx-community/UI-TARS-72B-SFT-4bit
4-bit
Vision + text ↓ 27 · ♥ 0
Params
73B
Weights
≈ 42.3 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-03-03

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

paligemma2-28b-mix-224-8bit

mlx-community/paligemma2-28b-mix-224-8bit
8-bit
Vision + text ↓ 27 · ♥ 0
Params
28B
Weights
≈ 29.8 GB
Mac memory
48 GB+

gemma · updated 2025-02-20

paligemma2-3b-ft-docci-448-6bit

mlx-community/paligemma2-3b-ft-docci-448-6bit
6-bit
Vision + text ↓ 27 · ♥ 0
Params
3.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+

gemma · updated 2024-12-05

gemma-4-31b-5bit

from google/gemma-4-31b
5-bit
Vision + text · Google · Gemma ↓ 26 · ♥ 2
Params
31B
Weights
≈ 22.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-02

LFM2-VL-1.6B-5bit

mlx-community/LFM2-VL-1.6B-5bit
5-bit
Vision + text ↓ 26 · ♥ 1
Params
1.6B
Weights
≈ 1.6 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-08-16

LFM2-VL-1.6B-6bit

mlx-community/LFM2-VL-1.6B-6bit
6-bit
Vision + text ↓ 26 · ♥ 1
Params
1.6B
Weights
≈ 1.8 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-08-16

LLaDA2.1-mini-5bit

from inclusionAI/LLaDA2.1-mini
5-bit
Vision + text · inclusionAI ↓ 26 · ♥ 0
Params
16B
Weights
≈ 11.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-05-30

Tess-4-27B-mxfp8

from migtissera/Tess-4-27B
MXFP8
Vision + text · migtissera ↓ 26 · ♥ 0
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-10

UI-TARS-72B-SFT-8bit

mlx-community/UI-TARS-72B-SFT-8bit
8-bit
Vision + text ↓ 26 · ♥ 0
Params
73B
Weights
≈ 78.7 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-03-03

paligemma2-3b-ft-docci-448-8bit

mlx-community/paligemma2-3b-ft-docci-448-8bit
8-bit
Vision + text ↓ 26 · ♥ 0
Params
3.0B
Weights
≈ 3.2 GB
Mac memory
8 GB+

gemma · updated 2024-12-05

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

aya-vision-32b-8bit

mlx-community/aya-vision-32b-8bit
8-bit
Vision + text ↓ 25 · ♥ 1
Params
33B
Weights
≈ 35.6 GB
Mac memory
48 GB+

cc-by-nc-4.0 · updated 2025-03-05

CodeFormulaV2-mlx-q8

from docling-project/CodeFormulaV2
8-bit
Vision + text · docling-project ↓ 25 · ♥ 0
Params
315M
Weights
≈ 416 MB
Mac memory
8 GB+

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

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

Holo2-8B-bf16

from Hcompany/Holo2-8B
bf16
Vision + text · Hcompany ↓ 25 · ♥ 0
Params
8.8B
Weights
≈ 17.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-11-17

InternVL3-38B-bf16

from OpenGVLab/InternVL3-1B-Instruct
bf16
Vision + text · OpenGVLab ↓ 25 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

Lance-3B-AWQ-INT4

from bytedance-research/Lance
4-bit
Vision + text · bytedance-research ↓ 25 · ♥ 0
Params
6.2B
Weights
≈ 3.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-26

Qwen3-VL-2B-Thinking-5bit

mlx-community/Qwen3-VL-2B-Thinking-5bit
5-bit
Vision + text ↓ 25 · ♥ 0
Params
2.1B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

UI-TARS-7B-SFT-6bit

mlx-community/UI-TARS-7B-SFT-6bit
6-bit
Vision + text ↓ 25 · ♥ 0
Params
8.3B
Weights
≈ 7.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-03

UI-Venus-1.5-8B-bf16

from inclusionAI/UI-Venus-1.5-8B
bf16
Vision + text · inclusionAI ↓ 25 · ♥ 0
Params
8.8B
Weights
≈ 17.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-03-20

gemma-3n-E2B-3bit

from google/gemma-3n-E4B
3-bit
Vision + text · Google · Gemma ↓ 25 · ♥ 0
Params
5.4B
Weights
≈ 3.9 GB
Mac memory
8 GB+

gemma · updated 2025-07-06

UI-TARS-72B-DPO-bf16

mlx-community/UI-TARS-72B-DPO-bf16
bf16
Vision + text ↓ 24 · ♥ 1
Params
73B
Weights
≈ 147 GB
Mac memory
192 GB+

apache-2.0 · updated 2025-03-06

dots.ocr-6bit

mlx-community/dots.ocr-6bit
6-bit
Vision + text ↓ 24 · ♥ 1
Params
3.0B
Weights
≈ 4.0 GB
Mac memory
8 GB+

mit · updated 2026-02-16

Bunny-Llama-3-8B-V-8bit

mlx-community/Bunny-Llama-3-8B-V-8bit
8-bit
Vision + text ↓ 24 · ♥ 0
Params
8.5B
Weights
≈ 9.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-08-01

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

Lingshu-7B-8bit

mlx-community/Lingshu-7B-8bit
8-bit
Vision + text ↓ 24 · ♥ 0
Params
—
Weights
—
Mac memory
—

mit · updated 2025-06-12

bu-30b-a3b-preview-8bit

from browser-use/bu-30b-a3b-preview
8-bit
Vision + text · browser-use ↓ 24 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2025-12-17

gemma-3-12b-it-qat-6bit

from OpenGVLab/InternVL3-1B-Instruct
6-bit
Vision + text · OpenGVLab ↓ 24 · ♥ 0
Params
—
Weights
—
Mac memory
—

qwen · updated 2025-04-21

gemma-3n-E2B-it-6bit

from google/gemma-3n-E4B-it
6-bit
Vision + text · Google · Gemma ↓ 24 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

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

PaddleOCR-VL-1.5-6bit

from baidu/ERNIE-4.5-0.3B-Paddle
6-bit
Vision + text · baidu ↓ 23 · ♥ 0
Params
906M
Weights
≈ 896 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-29

Qwen3-VL-2B-Thinking-3bit

mlx-community/Qwen3-VL-2B-Thinking-3bit
3-bit
Vision + text ↓ 23 · ♥ 0
Params
2.1B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

ShowUI-2B-bf16-v2

from showlab/ShowUI-2B
bf16
Vision + text · showlab ↓ 23 · ♥ 0
Params
2.4B
Weights
≈ 4.9 GB
Mac memory
8 GB+

mit · updated 2026-03-20

UI-TARS-72B-SFT-6bit

mlx-community/UI-TARS-72B-SFT-6bit
6-bit
Vision + text ↓ 23 · ♥ 0
Params
73B
Weights
≈ 60.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-03-03

UI-TARS-7B-DPO-bf16

mlx-community/UI-TARS-7B-DPO-bf16
bf16
Vision + text ↓ 23 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-03

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

gemma-3n-E2B-6bit

from google/gemma-3n-E4B
6-bit
Vision + text · Google · Gemma ↓ 23 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

lift-oQ5

from datalab-to/lift
5-bit
Vision + text · datalab-to ↓ 23 · ♥ 0
Params
9.4B
Weights
≈ 7.1 GB
Mac memory
16 GB+

openrail · updated 2026-06-27

llava-interleave-qwen-0.5b-6bit

mlx-community/llava-interleave-qwen-0.5b-6bit
6-bit
Vision + text ↓ 23 · ♥ 0
Params
864M
Weights
≈ 1.2 GB
Mac memory
8 GB+

tongyi-qianwen-research · updated 2025-03-27

llava-interleave-qwen-7b-8bit

mlx-community/llava-interleave-qwen-7b-8bit
8-bit
Vision + text ↓ 23 · ♥ 0
Params
—
Weights
—
Mac memory
—

tongyi-qianwen-research · updated 2025-03-27

llava-interleave-qwen-7b-bf16

mlx-community/llava-interleave-qwen-7b-bf16
bf16
Vision + text ↓ 23 · ♥ 0
Params
8.1B
Weights
≈ 16.3 GB
Mac memory
24 GB+

tongyi-qianwen-research · updated 2025-03-27

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

Gemma-3-Glitter-12B-8bit

from allura-org/Gemma-3-Glitter-12B
8-bit
Vision + text · allura-org ↓ 22 · ♥ 0
Params
12B
Weights
≈ 12.5 GB
Mac memory
16 GB+

updated 2025-09-29

Gemma-SEA-LION-v4-4B-VL-mlx-3bit

from google/gemma-3-4b-it
3-bit
Vision + text · Google · Gemma ↓ 22 · ♥ 0
Params
5.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-10

Qwen3-VL-2B-Thinking-6bit

mlx-community/Qwen3-VL-2B-Thinking-6bit
6-bit
Vision + text ↓ 22 · ♥ 0
Params
2.1B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

UGround-V1-2B-bf16

from osunlp/UGround-V1-2B
bf16
Vision + text · osunlp ↓ 22 · ♥ 0
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-22