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 6 of 18 · clear filters

Unlimited-OCR-mxfp8

from baidu/Unlimited-OCR
MXFP8
Vision + text · baidu ↓ 229 · ♥ 5
Params
3.3B
Weights
≈ 3.9 GB
Mac memory
8 GB+

mit · updated 2026-07-28

dots.mocr-8bit

from dots-studio/dots.mocr
8-bit
Vision + text · dots-studio ↓ 223 · ♥ 1
Params
3.0B
Weights
≈ 4.4 GB
Mac memory
8 GB+

mit · updated 2026-04-03

Qwopus3.8-27B-Flash-V2-4bit

from Jackrong/Qwopus3.8-27B-Flash-V2
4-bit
Vision + text · Jackrong ↓ 218 · ♥ 2
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-09-22

AREX-2-4bit

from BAAI/AREX-2
4-bit
Vision + text · BAAI ↓ 218 · ♥ 0
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-07

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

mlx-community/Qwen3-VL-30B-A3B-Instruct-8bit
8-bit
Vision + text ↓ 217 · ♥ 3
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-11

MiniCPM-V-4.7-1B-mxfp4

from openbmb/MiniCPM-V-4.7-1B
MXFP4
Vision + text · openbmb ↓ 214 · ♥ 0
Params
1.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

Qwen3.6-27B-6bit

from Qwen/Qwen3.6-27B
6-bit
Vision + text · Qwen ↓ 213 · ♥ 9
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-22

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

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B
4-bit
Vision + text · Jackrong ↓ 213 · ♥ 0
Params
4.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-07

SmolVLM-256M-Instruct-bf16

from HuggingFaceTB/SmolLM2-135M-Instruct
bf16
Vision + text · Hugging Face ↓ 212 · ♥ 1
Params
256M
Weights
≈ 513 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-01-23

gemma-4-e2b-it-mxfp4

from google/gemma-4-E2B-it
MXFP4
Vision + text · Google · Gemma ↓ 211 · ♥ 1
Params
5.1B
Weights
≈ 3.6 GB
Mac memory
8 GB+

gemma · updated 2026-07-06

Molmo2-8B-mxfp4

from allenai/Molmo2-8B
MXFP4
Vision + text · Ai2 · OLMo ↓ 210 · ♥ 0
Params
8.7B
Weights
≈ 6.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-20

UI-TARS-1.5-7B-6bit

mlx-community/UI-TARS-1.5-7B-6bit
6-bit
Vision + text ↓ 207 · ♥ 4
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-25

unsloth-gemma-4-31B-it-qat-oQ4

from unsloth/gemma-4-31B-it-qat-q4_0-unquantized
4-bit
Vision + text · unsloth ↓ 206 · ♥ 0
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-06-08

LFM2-VL-3B-4bit

mlx-community/LFM2-VL-3B-4bit
4-bit
Vision + text ↓ 205 · ♥ 4
Params
3.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-15

Qwen2.5-VL-72B-Instruct-8bit

from Qwen/Qwen2.5-VL-72B-Instruct
8-bit
Vision + text · Qwen ↓ 205 · ♥ 2
Params
73B
Weights
≈ 78.0 GB
Mac memory
96 GB+

qwen · updated 2025-02-25

gemma-4-26b-a4b-it-mxfp4

from google/gemma-4-26B-A4B-it
MXFP4
Vision + text · Google · Gemma ↓ 203 · ♥ 7
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-05

Qwen2.5-VL-32B-Instruct-bf16

mlx-community/Qwen2.5-VL-32B-Instruct-bf16
bf16
Vision + text ↓ 203 · ♥ 5
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-03-27

pixtral-12b-4bit

mlx-community/pixtral-12b-4bit
4-bit
Vision + text ↓ 202 · ♥ 7
Params
13B
Weights
≈ 7.1 GB
Mac memory
16 GB+

updated 2024-10-05

Qwen2.5-VL-72B-Instruct-3bit

from Qwen/Qwen2.5-VL-72B-Instruct
3-bit
Vision + text · Qwen ↓ 200 · ♥ 5
Params
73B
Weights
≈ 33.2 GB
Mac memory
48 GB+

qwen · updated 2025-02-25

MiniCPM-V-4.7-1B-nvfp4

from openbmb/MiniCPM-V-4.7-1B
4-bit
Vision + text · openbmb ↓ 200 · ♥ 0
Params
1.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

Kimi-VL-A3B-Thinking-2506-8bit

from moonshotai/Kimi-VL-A3B-Instruct
8-bit
Vision + text · Moonshot · Kimi ↓ 199 · ♥ 2
Params
—
Weights
—
Mac memory
—

mit · updated 2026-01-27

Kimi-VL-A3B-Thinking-2506-6bit

from moonshotai/Kimi-VL-A3B-Instruct
6-bit
Vision + text · Moonshot · Kimi ↓ 198 · ♥ 2
Params
—
Weights
—
Mac memory
—

mit · updated 2026-01-27

Qwen3-VL-2B-Instruct-8bit

mlx-community/Qwen3-VL-2B-Instruct-8bit
8-bit
Vision + text ↓ 197 · ♥ 1
Params
2.1B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-21

MiniCPM-V-4.7-1B-5bit

from openbmb/MiniCPM-V-4.7-1B
5-bit
Vision + text · openbmb ↓ 197 · ♥ 0
Params
1.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

MiniCPM-V-4.6-bf16

from openbmb/MiniCPM-V-4.6
bf16
Vision + text · openbmb ↓ 196 · ♥ 4
Params
1.3B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-13

deepseek-vl2-8bit

mlx-community/deepseek-vl2-8bit
8-bit
Vision + text ↓ 195 · ♥ 6
Params
27B
Weights
≈ 29.3 GB
Mac memory
48 GB+

deepseek · updated 2025-09-04

diffusiongemma-26B-A4B-it-nvfp4

from google/diffusiongemma-26B-A4B-it
4-bit
Vision + text · Google · Gemma ↓ 192 · ♥ 6
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-15

gemma-4-31b-it-nvfp4

from google/gemma-4-31B-it
4-bit
Vision + text · Google · Gemma ↓ 191 · ♥ 8
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

gemma · updated 2026-07-06

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

from mistralai/Ministral-3-3B-Base-2512
4-bit
Vision + text · Mistral ↓ 190 · ♥ 1
Params
3.8B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-18

LightOnOCR-3-1B-mlx-4bit

from lightonai/LightOnOCR-3-1B
4-bit
Vision + text · lightonai ↓ 189 · ♥ 0
Params
1.0B
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-17

Unlimited-OCR-bf16

from baidu/Unlimited-OCR
bf16
Vision + text · baidu ↓ 188 · ♥ 2
Params
3.3B
Weights
≈ 6.7 GB
Mac memory
16 GB+

mit · updated 2026-07-31

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

from Jackrong/Qwopus3.8-27B-Flash-V2
8-bit
Vision + text · Jackrong ↓ 188 · ♥ 0
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-09-22

Falcon-OCR-bf16

from tiiuae/Falcon-OCR
bf16
Vision + text · TII · Falcon ↓ 187 · ♥ 4
Params
270M
Weights
≈ 540 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-12

Fara1.5-27B-OptiQ-4bit

from microsoft/Fara1.5-27B
4-bit
Vision + text · Microsoft · Phi ↓ 187 · ♥ 2
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

mit · updated 2026-10-18

Tess-4-27B-OptiQ-4bit

from migtissera/Tess-4-27B
4-bit
Vision + text · migtissera ↓ 187 · ♥ 0
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-30

LocateAnything-3B-8bit

from nvidia/LocateAnything-3B
8-bit
Vision + text · NVIDIA ↓ 186 · ♥ 12
Params
3.5B
Weights
≈ 4.1 GB
Mac memory
8 GB+

nvidia-license · updated 2026-05-29

gemma-4-31B-it-qat-mxfp8

mlx-community/gemma-4-31B-it-qat-mxfp8
MXFP8
Vision + text ↓ 186 · ♥ 3
Params
31B
Weights
≈ 33.8 GB
Mac memory
48 GB+

updated 2026-06-05

Llama-4-Scout-17B-16E-Instruct-6bit

from meta-llama/Llama-4-Scout-17B-16E
6-bit
Vision + text · Meta · Llama ↓ 185 · ♥ 5
Params
—
Weights
—
Mac memory
—

llama4 · updated 2025-05-03

Nex-N2.5-mini-OptiQ-4bit

from nex-agi/Nex-N2.5-mini
4-bit
Vision + text · nex-agi ↓ 185 · ♥ 2
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-09-12

gemma-4-26B-A4B-it-qat-6bit

mlx-community/gemma-4-26B-A4B-it-qat-6bit
6-bit
Vision + text ↓ 183 · ♥ 2
Params
26B
Weights
≈ 21.6 GB
Mac memory
32 GB+

updated 2026-06-05

dots.ocr-8bit

mlx-community/dots.ocr-8bit
8-bit
Vision + text ↓ 183 · ♥ 0
Params
3.0B
Weights
≈ 4.4 GB
Mac memory
8 GB+

mit · updated 2026-02-17

Qwen3.5-397B-A17B-6bit

mlx-community/Qwen3.5-397B-A17B-6bit
6-bit
Vision + text ↓ 181 · ♥ 2
Params
397B
Weights
≈ 323 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-02-19

AREX-2-8bit

from BAAI/AREX-2
8-bit
Vision + text · BAAI ↓ 181 · ♥ 1
Params
27B
Weights
≈ 29.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-10-07

Muse-Glimmer-30B-5bit

from meta-models/Muse-Glimmer-30B
5-bit
Vision + text · meta-models ↓ 181 · ♥ 0
Params
30B
Weights
≈ 22.9 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-08-10

Qwen3-VL-4B-Instruct-3bit

mlx-community/Qwen3-VL-4B-Instruct-3bit
3-bit
Vision + text ↓ 179 · ♥ 5
Params
4.4B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-14

Qwopus3.8-27B-Flash-V2-6bit

from Jackrong/Qwopus3.8-27B-Flash-V2
6-bit
Vision + text · Jackrong ↓ 179 · ♥ 0
Params
27B
Weights
≈ 22.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-09-22

gemma-4-31b-it-mxfp8

from google/gemma-4-31B-it
MXFP8
Vision + text · Google · Gemma ↓ 178 · ♥ 9
Params
31B
Weights
≈ 33.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-05

Llama-4-Scout-17B-16E-Instruct-8bit

from meta-llama/Llama-4-Scout-17B-16E
8-bit
Vision + text · Meta · Llama ↓ 178 · ♥ 4
Params
—
Weights
—
Mac memory
—

llama4 · updated 2025-05-03

Qwen2.5-VL-3B-Instruct-bf16

from Qwen/Qwen2.5-VL-3B-Instruct
bf16
Vision + text · Qwen ↓ 178 · ♥ 4
Params
3.8B
Weights
≈ 7.5 GB
Mac memory
16 GB+

updated 2025-02-26

Nemotron-Parse-2.0-4bit

from nvidia/NVIDIA-Nemotron-Parse-2.0
4-bit
Vision + text · NVIDIA ↓ 178 · ♥ 0
Params
977M
Weights
≈ 1.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

gemma-4-E2B-it-qat-8bit

mlx-community/gemma-4-E2B-it-qat-8bit
8-bit
Vision + text ↓ 177 · ♥ 0
Params
5.1B
Weights
≈ 5.9 GB
Mac memory
16 GB+

updated 2026-06-05

Inkling-Small-mxfp4

from thinkingmachines/Inkling-Small
MXFP4
Vision + text · thinkingmachines ↓ 176 · ♥ 4
Params
264B
Weights
≈ 149 GB
Mac memory
192 GB+

updated 2026-07-30

medgemma-1.5-4b-it-8bit

mlx-community/medgemma-1.5-4b-it-8bit
8-bit
Vision + text ↓ 175 · ♥ 2
Params
5.0B
Weights
≈ 5.7 GB
Mac memory
16 GB+

health-ai-developer-foundations · updated 2026-01-14

Qwen2.5-VL-7B-Instruct-bf16

from Qwen/Qwen2.5-VL-7B-Instruct
bf16
Vision + text · Qwen ↓ 174 · ♥ 4
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-02-26

Qwen2.5-VL-7B-Instruct-3bit

from Qwen/Qwen2.5-VL-7B-Instruct
3-bit
Vision + text · Qwen ↓ 173 · ♥ 1
Params
8.3B
Weights
≈ 4.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-25

Qwen3-VL-8B-Instruct-bf16

mlx-community/Qwen3-VL-8B-Instruct-bf16
bf16
Vision + text ↓ 172 · ♥ 3
Params
8.8B
Weights
≈ 17.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-10-14

North-Mini-Code-1.0-bf16

from CohereLabs/North-Mini-Code-1.0
bf16
Vision + text · Cohere ↓ 171 · ♥ 3
Params
30B
Weights
≈ 61.0 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-06-09

gemma-4-26B-A4B-it-qat-mxfp4

mlx-community/gemma-4-26B-A4B-it-qat-mxfp4
MXFP4
Vision + text ↓ 171 · ♥ 2
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

updated 2026-06-05

gemma-4-31b-it-5bit

from google/gemma-4-31B-it
5-bit
Vision + text · Google · Gemma ↓ 169 · ♥ 3
Params
31B
Weights
≈ 22.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-07-05

Devstral-Small-2-24B-Instruct-2512-5bit

from mistralai/Devstral-Small-2-24B-Instruct-2512
5-bit
Vision + text · Mistral ↓ 169 · ♥ 0
Params
24B
Weights
≈ 18.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-04