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 53m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

1,022 builds · page 2 of 18 · clear filters

Llama-3.2-11B-Vision-Instruct-abliterated

from meta-llama/Llama-3.2-11B-Vision-Instruct
Vision + text · Meta · Llama ↓ 2.7K · ♥ 7
Params
11B
Weights
≈ 21.3 GB
Mac memory
32 GB+

llama3.2 · updated 2024-12-16

Qwen3.6-35B-A3B-bf16

from Qwen/Qwen3.6-35B-A3B
bf16
Vision + text · Qwen ↓ 2.7K · ♥ 11
Params
35B
Weights
≈ 70.2 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-04-16

Qwen3.6-27B-8bit

from Qwen/Qwen3.6-27B
8-bit
Vision + text · Qwen ↓ 2.7K · ♥ 20
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-22

gemma-3-4b-it-4bit

from google/gemma-3-4b-pt
4-bit
Vision + text · Google · Gemma ↓ 2.7K · ♥ 8
Params
5.0B
Weights
≈ 3.4 GB
Mac memory
8 GB+

gemma · updated 2025-03-21

Qwen3.6-35B-A3B-6bit

from Qwen/Qwen3.6-35B-A3B
6-bit
Vision + text · Qwen ↓ 2.6K · ♥ 11
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-16

Llama-3.2-11B-Vision-Instruct-4bit

from meta-llama/Llama-3.2-11B-Vision-Instruct
4-bit
Vision + text · Meta · Llama ↓ 2.6K · ♥ 8
Params
11B
Weights
≈ 6.0 GB
Mac memory
16 GB+

llama3.2 · updated 2024-10-18

Qwen2.5-VL-7B-Instruct-8bit

from Qwen/Qwen2.5-VL-7B-Instruct
8-bit
Vision + text · Qwen ↓ 2.5K · ♥ 17
Params
8.3B
Weights
≈ 8.9 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-02-25

Muse-Spark-Open-816B-A42B-oQ3e

from meta-models/Muse-Spark-Open-816B-A42B
3-bit
Vision + text · meta-models ↓ 2.5K · ♥ 7
Params
822B
Weights
≈ 366 GB
Mac memory
512 GB+

muse-model-license · updated 2026-10-16

Qwen3.8-27B-OBLITERATED-OptiQ-4bit

from OBLITERATUS/Qwen3.8-27B-OBLITERATED
4-bit
Vision + text · OBLITERATUS ↓ 2.4K · ♥ 9
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-30

gemma-4-26B-A4B-it-heretic-4bit

from coder3101/gemma-4-26B-A4B-it-heretic
4-bit
Vision + text · coder3101 ↓ 2.4K · ♥ 27
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-19

FastVLM-0.5B-bf16

mlx-community/FastVLM-0.5B-bf16
bf16
Vision + text ↓ 2.3K · ♥ 1
Params
623M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apple-amlr · updated 2025-10-18

Qwen3.8-Flash-Next-4bit-mtp

from Qwen/Qwen3.8-Flash-Next
4-bit
Vision + text · Qwen ↓ 2.3K · ♥ 6
Params
180B
Weights
≈ 102 GB
Mac memory
128 GB+

updated 2026-09-25

PaddleOCR-VL-1.5-4bit

from baidu/ERNIE-4.5-0.3B-Paddle
4-bit
Vision + text · baidu ↓ 2.3K · ♥ 3
Params
906M
Weights
≈ 703 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-29

DeepSeek-V4.1-Flash-1017-oQ2e-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017
Vision + text · DeepSeek ↓ 2.1K · ♥ 3
Params
95B
Weights
≈ 313 GB
Mac memory
512 GB+

mit · updated 2026-10-17

MiniCPM-V-4.7-35B-A3B-OptiQ-4bit-REAP-19B

from mlx-community/MiniCPM-V-4.7-35B-A3B-OptiQ-4bit
4-bit
Vision + text ↓ 2.0K · ♥ 6
Params
19B
Weights
≈ 11.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-13

Qwen3.8-Flash-Next-Uncensored-oQ6e-mtp

from orcarouter/Qwen3.8-Flash-Next-Uncensored
6-bit
Vision + text · orcarouter ↓ 2.0K · ♥ 5
Params
180B
Weights
≈ 147 GB
Mac memory
192 GB+

qwen-community-1.0 · updated 2026-09-16

Muse-Glimmer-30B-bf16

from meta-models/Muse-Glimmer-30B
bf16
Vision + text · meta-models ↓ 2.0K · ♥ 8
Params
30B
Weights
≈ 59.6 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-08-11

MiniCPM-V-4.7-35B-A3B-mxfp4

from openbmb/MiniCPM-V-4.7-35B-A3B
MXFP4
Vision + text · openbmb ↓ 2.0K · ♥ 4
Params
35B
Weights
≈ 23.5 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-13

Muse-Spark-Open-816B-A42B-3bit

from meta-models/Muse-Spark-Open-816B-A42B
3-bit
Vision + text · meta-models ↓ 1.9K · ♥ 4
Params
822B
Weights
≈ 436 GB
Mac memory
512 GB+

muse-model-license · updated 2026-10-16

gemma-4-e4b-it-8bit

from google/gemma-4-E4B-it
8-bit
Vision + text · Google · Gemma ↓ 1.9K · ♥ 30
Params
7.9B
Weights
≈ 8.9 GB
Mac memory
16 GB+

gemma · updated 2026-07-06

Qwen3.5-0.8B-bf16

from Qwen/Qwen3.5-0.8B-Base
bf16
Vision + text · Qwen ↓ 1.9K · ♥ 0
Params
853M
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-02

Qwen3.6-35B-A3B-nvfp4

from Qwen/Qwen3.6-35B-A3B
4-bit
Vision + text · Qwen ↓ 1.9K · ♥ 15
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-16

Muse-Spark-Open-816B-A42B-oQ4e

from meta-models/Muse-Spark-Open-816B-A42B
4-bit
Vision + text · meta-models ↓ 1.9K · ♥ 6
Params
822B
Weights
≈ 468 GB
Mac memory
> 512 GB

muse-model-license · updated 2026-10-16

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

from meta-llama/Llama-4-Scout-17B-16E
4-bit
Vision + text · Meta · Llama ↓ 1.9K · ♥ 12
Params
—
Weights
—
Mac memory
—

llama4 · updated 2025-05-03

Muse-Glimmer-30B-OptiQ-4bit

from meta-models/Muse-Glimmer-30B
4-bit
Vision + text · meta-models ↓ 1.8K · ♥ 8
Params
28B
Weights
≈ 19.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-13

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

mlx-community/gemma-4-E2B-it-qat-4bit
4-bit
Vision + text ↓ 1.8K · ♥ 4
Params
5.1B
Weights
≈ 3.6 GB
Mac memory
8 GB+

updated 2026-06-05

DeepSeek-V4.1-Flash-1017-oQ3e-ngram-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017
Vision + text · DeepSeek ↓ 1.8K · ♥ 4
Params
272B
Weights
≈ 455 GB
Mac memory
512 GB+

mit · updated 2026-10-29

Qwen2.5-VL-72B-Instruct-4bit

from Qwen/Qwen2.5-VL-72B-Instruct
4-bit
Vision + text · Qwen ↓ 1.8K · ♥ 11
Params
73B
Weights
≈ 42.3 GB
Mac memory
64 GB+

qwen · updated 2025-02-25

gemma-3-12b-it-bf16

from google/gemma-3-12b-pt
bf16
Vision + text · Google · Gemma ↓ 1.7K · ♥ 2
Params
13B
Weights
≈ 26.4 GB
Mac memory
32 GB+

gemma · updated 2025-03-19

diffusiongemma-26B-A4B-it-4bit

from google/diffusiongemma-26B-A4B-it
4-bit
Vision + text · Google · Gemma ↓ 1.7K · ♥ 37
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-15

Qwen3.5-9B-bf16

from Qwen/Qwen3.5-9B-Base
bf16
Vision + text · Qwen ↓ 1.7K · ♥ 5
Params
9.4B
Weights
≈ 18.8 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-03-02

Muse-Glimmer-30B-8bit

from meta-models/Muse-Glimmer-30B
8-bit
Vision + text · meta-models ↓ 1.7K · ♥ 4
Params
30B
Weights
≈ 33.4 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-08-10

DeepSeek-OCR-8bit

mlx-community/DeepSeek-OCR-8bit
8-bit
Vision + text ↓ 1.7K · ♥ 38
Params
3.3B
Weights
≈ 3.9 GB
Mac memory
8 GB+

mit · updated 2026-01-28

Qwen3.5-35B-A3B-8bit

mlx-community/Qwen3.5-35B-A3B-8bit
8-bit
Vision + text ↓ 1.7K · ♥ 23
Params
35B
Weights
≈ 37.7 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-02-24

Qwen3.5-122B-A10B-bf16

mlx-community/Qwen3.5-122B-A10B-bf16
bf16
Vision + text ↓ 1.7K · ♥ 2
Params
123B
Weights
≈ 245 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-02-25

DeepSeek-V4.1-Flash-1017-oQ3e-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017
Vision + text · DeepSeek ↓ 1.6K · ♥ 1
Params
112B
Weights
≈ 381 GB
Mac memory
512 GB+

mit · updated 2026-10-29

Qwen3.6-35B-A3B-mxfp8

from Qwen/Qwen3.6-35B-A3B
MXFP8
Vision + text · Qwen ↓ 1.6K · ♥ 8
Params
35B
Weights
≈ 37.7 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-05-14

DeepSeek-V4-Pro-Qwen3.5-9B-4bit

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
4-bit
Vision + text · Jackrong ↓ 1.6K · ♥ 4
Params
9.4B
Weights
≈ 6.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-07

gemma-4-31b-it-bf16

from google/gemma-4-31B-it
bf16
Vision + text · Google · Gemma ↓ 1.5K · ♥ 14
Params
31B
Weights
≈ 62.5 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-07-05

Qwen3.6-27B-nvfp4

from Qwen/Qwen3.6-27B
4-bit
Vision + text · Qwen ↓ 1.5K · ♥ 9
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-22

Mistral-Medium-3.5-128B-4bit

mlx-community/Mistral-Medium-3.5-128B-4bit
4-bit
Vision + text ↓ 1.5K · ♥ 5
Params
128B
Weights
≈ 78.0 GB
Mac memory
96 GB+

updated 2026-04-30

Qwen3-VL-30B-A3B-Instruct-4bit

mlx-community/Qwen3-VL-30B-A3B-Instruct-4bit
4-bit
Vision + text ↓ 1.5K · ♥ 9
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-11

gemma-4-e2b-it-bf16

from google/gemma-4-E2B-it
bf16
Vision + text · Google · Gemma ↓ 1.5K · ♥ 1
Params
5.1B
Weights
≈ 10.2 GB
Mac memory
16 GB+

gemma · updated 2026-07-06

PaddleOCR-VL-1.6-4bit

from PaddlePaddle/PaddleOCR-VL-1.6
4-bit
Vision + text · PaddlePaddle ↓ 1.5K · ♥ 3
Params
906M
Weights
≈ 703 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Qwen3.5-35B-A3B-bf16

mlx-community/Qwen3.5-35B-A3B-bf16
bf16
Vision + text ↓ 1.5K · ♥ 1
Params
35B
Weights
≈ 70.2 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-02-24

Qwen3.5-27B-bf16

mlx-community/Qwen3.5-27B-bf16
bf16
Vision + text ↓ 1.5K · ♥ 0
Params
27B
Weights
≈ 54.7 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-02-24

gemma-4-31B-it-uncensored-heretic-4bit

from llmfan46/gemma-4-31B-it-uncensored-heretic
4-bit
Vision + text · llmfan46 ↓ 1.4K · ♥ 6
Params
31B
Weights
≈ 17.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-05-19

LFM2.5-VL-450M-6bit

from LiquidAI/LFM2.5-VL-450M
6-bit
Vision + text · LiquidAI ↓ 1.4K · ♥ 0
Params
449M
Weights
≈ 467 MB
Mac memory
8 GB+

lfm1.0 · updated 2026-08-13

gemma-4-12B-it-8bit

mlx-community/gemma-4-12B-it-8bit
8-bit
Vision + text ↓ 1.4K · ♥ 42
Params
12B
Weights
≈ 12.7 GB
Mac memory
24 GB+

updated 2026-06-08

DeepSeek-V4.1-Flash-1017-oQ2.5e-ngram-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017
Vision + text · DeepSeek ↓ 1.3K · ♥ 3
Params
262B
Weights
≈ 416 GB
Mac memory
512 GB+

mit · updated 2026-10-22

Sage-A1.5-OptiQ-4bit

from InternScience/Sage-A1.5
4-bit
Vision + text · InternScience ↓ 1.3K · ♥ 5
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-10-30

SmolVLM-256M-Instruct-4bit

from HuggingFaceTB/SmolLM2-135M-Instruct
4-bit
Vision + text · Hugging Face ↓ 1.3K · ♥ 0
Params
256M
Weights
≈ 145 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-23

Unlimited-OCR-2-8bit

from baidu/Unlimited-OCR-2
8-bit
Vision + text · baidu ↓ 1.3K · ♥ 5
Params
3.3B
Weights
≈ 3.9 GB
Mac memory
8 GB+

mit · updated 2026-10-27

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

mlx-community/gemma-4-31B-it-qat-4bit
4-bit
Vision + text ↓ 1.3K · ♥ 7
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

updated 2026-06-05

Qwen2-VL-7B-Instruct-4bit

mlx-community/Qwen2-VL-7B-Instruct-4bit
4-bit
Vision + text ↓ 1.2K · ♥ 3
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-03-24

Qwen3.5-9B-6bit

from Qwen/Qwen3.5-9B-Base
6-bit
Vision + text · Qwen ↓ 1.2K · ♥ 7
Params
9.4B
Weights
≈ 8.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-02

MiniMax-M3.1-Flash-oQ4e-mtp

from MiniMaxAI/MiniMax-M3.1-Flash
4-bit
Vision + text · MiniMaxAI ↓ 1.2K · ♥ 4
Params
427B
Weights
≈ 241 GB
Mac memory
512 GB+

minimax-community · updated 2026-10-23

gemma-3n-E2B-it-4bit

from google/gemma-3n-E4B-it
4-bit
Vision + text · Google · Gemma ↓ 1.2K · ♥ 10
Params
5.4B
Weights
≈ 4.5 GB
Mac memory
8 GB+

gemma · updated 2025-07-12