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 5 of 18 · clear filters

GOT-OCR2_0-4bit

from stepfun-ai/GOT-OCR2_0
4-bit
Vision + text · stepfun-ai ↓ 376 · ♥ 0
Params
561M
Weights
≈ 454 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-14

gemma-4-26b-a4b-it-nvfp4

from google/gemma-4-26B-A4B-it
4-bit
Vision + text · Google · Gemma ↓ 371 · ♥ 17
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-05

Groot-19B-A3B-OptiQ-4bit

from GrootTeam/Groot-19B-A3B-261023
4-bit
Vision + text · GrootTeam ↓ 371 · ♥ 1
Params
19B
Weights
≈ 11.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-11-05

gemma-4-12B-it-qat-nvfp4

mlx-community/gemma-4-12B-it-qat-nvfp4
4-bit
Vision + text ↓ 370 · ♥ 1
Params
12B
Weights
≈ 6.7 GB
Mac memory
16 GB+

updated 2026-06-05

LensVLM-9B-OptiQ-4bit

from apple/LensVLM-9B
4-bit
Vision + text · apple ↓ 360 · ♥ 5
Params
9.0B
Weights
≈ 6.0 GB
Mac memory
16 GB+

apple-amlr · updated 2026-10-18

Muse-Glimmer-30B-nvfp4

from meta-models/Muse-Glimmer-30B
4-bit
Vision + text · meta-models ↓ 360 · ♥ 2
Params
30B
Weights
≈ 19.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-08-11

gemma-4-12B-it-mxfp8

mlx-community/gemma-4-12B-it-mxfp8
MXFP8
Vision + text ↓ 359 · ♥ 4
Params
12B
Weights
≈ 12.7 GB
Mac memory
24 GB+

updated 2026-06-08

gemma-4-26b-a4b-4bit

from google/gemma-4-26b-a4b
4-bit
Vision + text · Google · Gemma ↓ 357 · ♥ 20
Params
26B
Weights
≈ 15.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-03

ThinkingCap-Qwen3.6-27B-OptiQ-4bit

from bottlecapai/ThinkingCap-Qwen3.6-27B
4-bit
Vision + text · bottlecapai ↓ 357 · ♥ 4
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-30

Ternary-Bonsai-2-2B-2bit

from Qwen/Qwen3.5-2B
2-bit
Vision + text · Qwen ↓ 356 · ♥ 0
Params
2.2B
Weights
≈ 1.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-15

Qwen3.5-122B-A10B-OptiQ-2bit

from Qwen/Qwen3.5-122B-A10B
2-bit
Vision + text · Qwen ↓ 353 · ♥ 6
Params
122B
Weights
≈ 39.1 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-09-15

MiniCPM-V-4.7-35B-A3B-5bit

from openbmb/MiniCPM-V-4.7-35B-A3B
5-bit
Vision + text · openbmb ↓ 353 · ♥ 1
Params
35B
Weights
≈ 27.6 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-10-13

gemma-4-12B-it-qat-5bit

mlx-community/gemma-4-12B-it-qat-5bit
5-bit
Vision + text ↓ 353 · ♥ 0
Params
12B
Weights
≈ 8.2 GB
Mac memory
16 GB+

updated 2026-06-05

Qwen3.5-0.8B-6bit

from Qwen/Qwen3.5-0.8B-Base
6-bit
Vision + text · Qwen ↓ 349 · ♥ 0
Params
853M
Weights
≈ 813 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-02

DeepSeek-V4-Pro-Qwen3.5-9B-6bit

from Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B
6-bit
Vision + text · Jackrong ↓ 344 · ♥ 1
Params
9.4B
Weights
≈ 8.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-08-07

Unlimited-OCR-2-6bit

from baidu/Unlimited-OCR-2
6-bit
Vision + text · baidu ↓ 343 · ♥ 1
Params
3.3B
Weights
≈ 3.2 GB
Mac memory
8 GB+

mit · updated 2026-10-27

gemma-3-12b-it-8bit

from google/gemma-3-12b-pt
8-bit
Vision + text · Google · Gemma ↓ 336 · ♥ 2
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-03-19

DeepSeek-OCR-2-4bit

mlx-community/DeepSeek-OCR-2-4bit
4-bit
Vision + text ↓ 329 · ♥ 2
Params
3.4B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-28

gemma-4-12B-it-qat-bf16

mlx-community/gemma-4-12B-it-qat-bf16
bf16
Vision + text ↓ 327 · ♥ 0
Params
12B
Weights
≈ 23.9 GB
Mac memory
32 GB+

updated 2026-06-05

gemma-4-31B-it-qat-8bit

mlx-community/gemma-4-31B-it-qat-8bit
8-bit
Vision + text ↓ 320 · ♥ 3
Params
31B
Weights
≈ 33.8 GB
Mac memory
48 GB+

updated 2026-06-05

Mage-VL-8bit

from microsoft/Mage-VL
8-bit
Vision + text · Microsoft · Phi ↓ 317 · ♥ 10
Params
4.7B
Weights
≈ 5.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-29

Astrea-R8-Chat-9B-OptiQ-4bit

from HemmingwayAI/Astrea-R8-Chat-9B
4-bit
Vision + text · HemmingwayAI ↓ 309 · ♥ 2
Params
9.0B
Weights
≈ 6.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-23

Ornith-1.0-9B-OptiQ-4bit

from ornith-ai/Ornith-1.0-9B
4-bit
Vision + text · ornith-ai ↓ 308 · ♥ 9
Params
9.0B
Weights
≈ 6.0 GB
Mac memory
16 GB+

mit · updated 2026-10-18

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-8bit

from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
8-bit
Vision + text · NVIDIA ↓ 308 · ♥ 2
Params
33B
Weights
≈ 35.8 GB
Mac memory
48 GB+

nvidia-open-model-agreement · updated 2026-04-29

Qwen3.5-122B-A10B-5bit

mlx-community/Qwen3.5-122B-A10B-5bit
5-bit
Vision + text ↓ 308 · ♥ 2
Params
123B
Weights
≈ 84.9 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-02-24

Qwythos-27B-v1-OptiQ-4bit

from empero-ai/Qwythos-27B-v1
4-bit
Vision + text · empero-ai ↓ 306 · ♥ 2
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-30

MiniCPM-V-4.7-1B-mxfp8

from openbmb/MiniCPM-V-4.7-1B
MXFP8
Vision + text · openbmb ↓ 302 · ♥ 1
Params
1.6B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

medgemma-27b-it-8bit

from google/gemma-3-27b-pt
8-bit
Vision + text · Google · Gemma ↓ 301 · ♥ 5
Params
—
Weights
—
Mac memory
—

health-ai-developer-foundations · updated 2025-07-10

AREX-2-5bit

from BAAI/AREX-2
5-bit
Vision + text · BAAI ↓ 299 · ♥ 4
Params
27B
Weights
≈ 19.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-10-07

gemma-4-e2b-it-6bit

from google/gemma-4-E2B-it
6-bit
Vision + text · Google · Gemma ↓ 298 · ♥ 0
Params
5.1B
Weights
≈ 4.7 GB
Mac memory
8 GB+

gemma · updated 2026-07-06

GLM-4.6V-Flash-4bit

mlx-community/GLM-4.6V-Flash-4bit
4-bit
Vision + text ↓ 287 · ♥ 7
Params
—
Weights
—
Mac memory
—

mit · updated 2025-12-08

LFM2-VL-450M-8bit

mlx-community/LFM2-VL-450M-8bit
8-bit
Vision + text ↓ 285 · ♥ 11
Params
451M
Weights
≈ 560 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-08-16

Devstral-Small-2-24B-Instruct-2512-bf16

from mistralai/Devstral-Small-2-24B-Instruct-2512
bf16
Vision + text · Mistral ↓ 285 · ♥ 4
Params
24B
Weights
≈ 48.0 GB
Mac memory
64 GB+

apache-2.0 · updated 2026-07-04

gemma-4-31b-it-mxfp4

from google/gemma-4-31B-it
MXFP4
Vision + text · Google · Gemma ↓ 283 · ♥ 6
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-05

Qwen3-VL-8B-Instruct-5bit

mlx-community/Qwen3-VL-8B-Instruct-5bit
5-bit
Vision + text ↓ 283 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-14

diffusiongemma-26B-A4B-it-8bit

from google/diffusiongemma-26B-A4B-it
8-bit
Vision + text · Google · Gemma ↓ 276 · ♥ 14
Params
26B
Weights
≈ 28.0 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-07-15

LightOnOCR-2-1B-bf16

mlx-community/LightOnOCR-2-1B-bf16
bf16
Vision + text ↓ 276 · ♥ 4
Params
1.0B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-06

Qwen3.5-9B-5bit

from Qwen/Qwen3.5-9B-Base
5-bit
Vision + text · Qwen ↓ 276 · ♥ 0
Params
9.4B
Weights
≈ 7.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-02

gemma-4-31b-4bit

from google/gemma-4-31b
4-bit
Vision + text · Google · Gemma ↓ 274 · ♥ 14
Params
31B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-04-02

Inkling-mlx-4bit

from thinkingmachines/Inkling
4-bit
Vision + text · thinkingmachines ↓ 270 · ♥ 7
Params
947B
Weights
≈ 549 GB
Mac memory
> 512 GB

apache-2.0 · updated 2026-07-24

Nemotron-Parse-2.0-8bit

from nvidia/NVIDIA-Nemotron-Parse-2.0
8-bit
Vision + text · NVIDIA ↓ 269 · ♥ 1
Params
977M
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

gemma-4-e4b-it-mxfp4

from google/gemma-4-E4B-it
MXFP4
Vision + text · Google · Gemma ↓ 268 · ♥ 4
Params
7.9B
Weights
≈ 5.1 GB
Mac memory
8 GB+

gemma · updated 2026-07-06

Inkling-Small-mlx-2bit

from thinkingmachines/Inkling-Small
2-bit
Vision + text · thinkingmachines ↓ 268 · ♥ 3
Params
264B
Weights
≈ 88.4 GB
Mac memory
128 GB+

apache-2.0 · updated 2026-07-31

InternVL3_5-1B-4bit

from OpenGVLab/InternVL3_5-1B-MPO
4-bit
Vision + text · OpenGVLab ↓ 268 · ♥ 0
Params
1.1B
Weights
≈ 1.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-04

Qwen3.6-35B-A3B-mxfp4

from Qwen/Qwen3.6-35B-A3B
MXFP4
Vision + text · Qwen ↓ 261 · ♥ 5
Params
35B
Weights
≈ 20.4 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-16

Kimi-VL-A3B-Thinking-8bit

from OpenGVLab/InternVL3-1B-Instruct
8-bit
Vision + text · OpenGVLab ↓ 260 · ♥ 4
Params
—
Weights
—
Mac memory
—

qwen · updated 2026-01-27

Huihui-GLM-4.5V-abliterated-mxfp4

from zai-org/GLM-4.5V
MXFP4
Vision + text · zai-org ↓ 259 · ♥ 4
Params
108B
Weights
≈ 61.9 GB
Mac memory
96 GB+

mit · updated 2025-09-27

Qwen3.5-122B-A10B-oQ4-mtp

mlx-community/Qwen3.5-122B-A10B-oQ4-mtp
4-bit
Vision + text ↓ 258 · ♥ 4
Params
125B
Weights
≈ 71.1 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-05-28

MiniCPM-V-4.7-1B-6bit

from openbmb/MiniCPM-V-4.7-1B
6-bit
Vision + text · openbmb ↓ 258 · ♥ 1
Params
1.6B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-13

OvisOCR2-8bit

from ATH-MaaS/OvisOCR2
8-bit
Vision + text · ATH-MaaS ↓ 255 · ♥ 1
Params
853M
Weights
≈ 1.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-04

Qwen3-VL-32B-Instruct-8bit

mlx-community/Qwen3-VL-32B-Instruct-8bit
8-bit
Vision + text ↓ 248 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

LightOnOCR-3-1B-mlx-8bit

from lightonai/LightOnOCR-3-1B
8-bit
Vision + text · lightonai ↓ 248 · ♥ 0
Params
1.0B
Weights
≈ 1.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-17

Qwen2.5-VL-3B-Instruct-8bit

from Qwen/Qwen2.5-VL-3B-Instruct
8-bit
Vision + text · Qwen ↓ 246 · ♥ 7
Params
3.8B
Weights
≈ 4.1 GB
Mac memory
8 GB+

updated 2025-02-26

gemma-4-e4b-it-mxfp8

from google/gemma-4-E4B-it
MXFP8
Vision + text · Google · Gemma ↓ 240 · ♥ 9
Params
7.9B
Weights
≈ 8.9 GB
Mac memory
16 GB+

gemma · updated 2026-07-06

gemma-4-e4b-it-nvfp4

from google/gemma-4-E4B-it
4-bit
Vision + text · Google · Gemma ↓ 239 · ♥ 7
Params
7.9B
Weights
≈ 5.1 GB
Mac memory
8 GB+

gemma · updated 2026-07-06

Inkling-mlx-2bit

from thinkingmachines/Inkling
2-bit
Vision + text · thinkingmachines ↓ 237 · ♥ 6
Params
947B
Weights
≈ 315 GB
Mac memory
512 GB+

apache-2.0 · updated 2026-07-24

Inkling-Small-mlx-4bit

from thinkingmachines/Inkling-Small
4-bit
Vision + text · thinkingmachines ↓ 233 · ♥ 1
Params
264B
Weights
≈ 153 GB
Mac memory
192 GB+

apache-2.0 · updated 2026-07-31