UI-TARS-7B-SFT-4bit
mlx-community/UI-TARS-7B-SFT-4bit
Params
8.3B
Weights
≈ 5.6 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-03
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 14 of 18 · clear filters
granite-4.0-3b-vision-6bit
from ibm-granite/granite-4.0-3b-vision
Params
4.3B
Weights
≈ 4.0 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
Qwen3.5-35B-A3B-GPTQ-Int4
from Qwen/Qwen3.5-35B-A3B
Params
7.0B
Weights
≈ 8.2 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-03
gemma-4-31b-nvfp4
from google/gemma-4-31b
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-04-02
Apriel-1.5-15b-Thinker-6bit-MLX
from ServiceNow-AI/Apriel-1.5-15b-Thinker
Params
—
Weights
—
Mac memory
—
mit · updated 2025-10-03
UI-TARS-72B-SFT-bf16
mlx-community/UI-TARS-72B-SFT-bf16
Params
73B
Weights
≈ 147 GB
Mac memory
192 GB+
apache-2.0 · updated 2025-03-03
InternVL3-38B-8bit
from OpenGVLab/InternVL3-1B-Instruct
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-04-30
InternVL3-8B-3bit
from OpenGVLab/InternVL3-1B-Instruct
Params
7.9B
Weights
≈ 4.0 GB
Mac memory
8 GB+
qwen · updated 2025-04-18
North-Micro-Vision-Instruct-5bit
from CohereLabs/North-Micro-Vision-Instruct
Params
2.5B
Weights
≈ 2.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-08-12
UI-Venus-1.5-8B-6bit
from inclusionAI/UI-Venus-1.5-8B
Params
8.8B
Weights
≈ 7.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-20
aya-vision-8b-bf16
mlx-community/aya-vision-8b-bf16
Params
8.6B
Weights
≈ 17.3 GB
Mac memory
24 GB+
cc-by-nc-4.0 · updated 2025-03-05
dots.mocr-6bit
from dots-studio/dots.mocr
Params
3.0B
Weights
≈ 4.0 GB
Mac memory
8 GB+
mit · updated 2026-04-03
dots.ocr-mxfp4
mlx-community/dots.ocr-mxfp4
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+
mit · updated 2026-02-17
gemma-4-E2B-it-qat-bf16
mlx-community/gemma-4-E2B-it-qat-bf16
Params
5.1B
Weights
≈ 10.2 GB
Mac memory
16 GB+
updated 2026-06-05
holo1.5-7b-mlx
from Qwen/Qwen2.5-VL-7B-Instruct
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-09-17
lift-oQ4
from datalab-to/lift
Params
9.4B
Weights
≈ 6.0 GB
Mac memory
16 GB+
openrail · updated 2026-06-27
gemma-3-27b-pt-bf16
mlx-community/gemma-3-27b-pt-bf16
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-03-18
Qwen2-VL-7B-8bit
mlx-community/Qwen2-VL-7B-8bit
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-03-24
Qwen3.5-27B-GPTQ-Int4
mlx-community/Qwen3.5-27B-GPTQ-Int4
Params
12B
Weights
≈ 21.3 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-03-05
llava-interleave-qwen-0.5b-8bit
mlx-community/llava-interleave-qwen-0.5b-8bit
Params
864M
Weights
≈ 1.3 GB
Mac memory
8 GB+
tongyi-qianwen-research · updated 2025-03-27
paligemma2-10b-ft-docci-448-6bit
mlx-community/paligemma2-10b-ft-docci-448-6bit
Params
9.7B
Weights
≈ 7.9 GB
Mac memory
16 GB+
gemma · updated 2024-12-06
paligemma2-3b-mix-224-4bit
mlx-community/paligemma2-3b-mix-224-4bit
Params
3.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+
gemma · updated 2025-02-19
Fara-7B-4bit
from microsoft/Fara-7B
Params
8.3B
Weights
≈ 5.6 GB
Mac memory
16 GB+
mit · updated 2026-07-31
Idefics3-8B-Llama3-8bit
mlx-community/Idefics3-8B-Llama3-8bit
Params
8.5B
Weights
≈ 9.4 GB
Mac memory
16 GB+
apache-2.0 · updated 2025-01-30
MAI-UI-8B-4bit
from Tongyi-MAI/MAI-UI-8B
Params
8.8B
Weights
≈ 6.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-20
MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16
from INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0
Params
27B
Weights
≈ 54.0 GB
Mac memory
64 GB+
gemma · updated 2026-06-05
Qwen3-VL-30B-A3B-Instruct-5bit
mlx-community/Qwen3-VL-30B-A3B-Instruct-5bit
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-10-11
Qwen3-VL-4B-Thinking-5bit
mlx-community/Qwen3-VL-4B-Thinking-5bit
Params
4.4B
Weights
≈ 3.6 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-10-14
chandra-5bit
mlx-community/chandra-5bit
Params
—
Weights
—
Mac memory
—
openrail · updated 2025-10-21
granite-vision-3.2-2b-5bit
from ibm-granite/granite-vision-3.2-2b
Params
3.1B
Weights
≈ 2.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
granite-vision-3.2-2b-mxfp8
from ibm-granite/granite-vision-3.2-2b
Params
3.1B
Weights
≈ 3.7 GB
Mac memory
8 GB+
apache-2.0 · updated 2026-04-01
QVQ-72B-Preview-4bit
from Qwen/Qwen2-VL-72B
Params
73B
Weights
≈ 41.3 GB
Mac memory
64 GB+
qwen · updated 2025-04-12
gemma-4-31b-mxfp8
from google/gemma-4-31b
Params
31B
Weights
≈ 33.8 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-04-02
Holo1-3B-3bit
from Qwen/Qwen2.5-VL-3B-Instruct
Params
3.8B
Weights
≈ 2.7 GB
Mac memory
8 GB+
other · updated 2025-06-03
P1-VL-30B-A3B-8bit
from PRIME-RL/P1-VL-30B-A3B
Params
31B
Weights
≈ 33.5 GB
Mac memory
48 GB+
apache-2.0 · updated 2026-05-18
ERNIE-4.5-VL-28B-A3B-Thinking-5bit
mlx-community/ERNIE-4.5-VL-28B-A3B-Thinking-5bit
Params
29B
Weights
≈ 21.0 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-01-28
Holo1-7B-6bit
from Qwen/Qwen2.5-VL-7B-Instruct
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-06-03
InternVL3-78B-4bit
from OpenGVLab/InternVL3-1B-Instruct
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-04-30
LFM2-VL-3B-6bit
mlx-community/LFM2-VL-3B-6bit
Params
3.0B
Weights
≈ 2.9 GB
Mac memory
8 GB+
lfm1.0 · updated 2026-01-15
MolmoPoint-8B-fp16
from Qwen/Qwen3-8B
Params
8.7B
Weights
≈ 17.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-03-21
MolmoPoint-8B-mxfp8
from Qwen/Qwen3-8B
Params
8.7B
Weights
≈ 10.7 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-21
Qwen2-VL-2B-bf16
mlx-community/Qwen2-VL-2B-bf16
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-03-24
dots.ocr-nvfp4
mlx-community/dots.ocr-nvfp4
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+
mit · updated 2026-02-17
paligemma2-28b-mix-448-6bit
mlx-community/paligemma2-28b-mix-448-6bit
Params
28B
Weights
≈ 23.0 GB
Mac memory
32 GB+
gemma · updated 2025-02-20
gemma-4-31b-mxfp4
from google/gemma-4-31b
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+
apache-2.0 · updated 2026-04-02
LFM2-VL-1.6B-bf16
mlx-community/LFM2-VL-1.6B-bf16
Params
1.6B
Weights
≈ 3.2 GB
Mac memory
8 GB+
lfm1.0 · updated 2025-08-16
Nanonets-OCR-s-4bit
from Qwen/Qwen2.5-VL-3B-Instruct
Params
3.8B
Weights
≈ 3.1 GB
Mac memory
8 GB+
updated 2025-07-25
gemma-3-27b-pt-6bit
mlx-community/gemma-3-27b-pt-6bit
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-03-18
gemma-3-4b-it-qat-8bit
from google/gemma-3-4b-it
Params
5.0B
Weights
≈ 5.7 GB
Mac memory
16 GB+
gemma · updated 2025-04-18
gemma-3n-E2B-5bit
from google/gemma-3n-E4B
Params
5.4B
Weights
≈ 5.0 GB
Mac memory
8 GB+
gemma · updated 2025-07-12
Qwopus3.6-27B-Coder-6bit
from Jackrong/Qwopus3.6-27B-Coder
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+
apache-2.0 · updated 2026-07-01
gemma-3-12b-it-qat-8bit
from OpenGVLab/InternVL3-1B-Instruct
Params
—
Weights
—
Mac memory
—
qwen · updated 2025-04-21
gemma-3-27b-pt-8bit
mlx-community/gemma-3-27b-pt-8bit
Params
—
Weights
—
Mac memory
—
gemma · updated 2025-03-18
gemma-3-4b-it-qat-bf16
from google/gemma-3-4b-it
Params
5.0B
Weights
≈ 9.9 GB
Mac memory
16 GB+
gemma · updated 2025-04-18
Gelato-30B-A3B-4bit
from mlfoundations/Gelato-30B-A3B
Params
—
Weights
—
Mac memory
—
apache-2.0 · updated 2025-11-17
MAI-UI-8B-6bit
from Tongyi-MAI/MAI-UI-8B
Params
8.8B
Weights
≈ 9.0 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-20
Qwen-3-VL-Ricoh-8B-20260227-MLX-8bit
from ricoh-ai/Qwen-3-VL-Ricoh-8B-20260227
Params
8.8B
Weights
≈ 9.9 GB
Mac memory
16 GB+
apache-2.0 · updated 2026-03-30
Qwen3-VL-8B-Thinking-bf16
mlx-community/Qwen3-VL-8B-Thinking-bf16
Params
8.8B
Weights
≈ 17.5 GB
Mac memory
24 GB+
apache-2.0 · updated 2025-10-14
UGround-V1-2B
from Qwen/Qwen2-VL-2B
Params
2.2B
Weights
≈ 4.4 GB
Mac memory
8 GB+
apache-2.0 · updated 2025-06-04
aya-vision-32b-4bit
mlx-community/aya-vision-32b-4bit
Params
33B
Weights
≈ 19.2 GB
Mac memory
24 GB+
cc-by-nc-4.0 · updated 2025-03-05