Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,842 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

5,842 builds · page 53 of 98

Holo3-35B-A3B-8bit

from Hcompany/Holo3-35B-A3B
8-bit
Vision + text · Hcompany ↓ 50 · ♥ 1
Params
35B
Weights
≈ 38.6 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-02

Qwen2-57B-A14B-Instruct-8bit

mlx-community/Qwen2-57B-A14B-Instruct-8bit
8-bit
Text generation ↓ 50 · ♥ 1
Params
57B
Weights
≈ 61.0 GB
Mac memory
96 GB+

apache-2.0 · updated 2024-06-06

Tmax-9B-MLX-4bit

from allenai/tmax-9b
4-bit
Text generation · Ai2 · OLMo ↓ 50 · ♥ 1
Params
9.0B
Weights
≈ 5.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-25

V-JEPA2-vitl-fpc64-256

mlx-community/V-JEPA2-vitl-fpc64-256
Video classification ↓ 50 · ♥ 1
Params
326M
Weights
≈ 652 MB
Mac memory
8 GB+

mit · updated 2026-06-06

gemma-3-27b-it-qat-3bit

from OpenGVLab/InternVL3-1B-Instruct
3-bit
Vision + text · OpenGVLab ↓ 50 · ♥ 1
Params
—
Weights
—
Mac memory
—

qwen · updated 2025-04-19

nanoLLaVA-1.5-4bit

mlx-community/nanoLLaVA-1.5-4bit
4-bit
Uncategorised ↓ 50 · ♥ 1
Params
1.1B
Weights
≈ 594 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-12-26

Bernini-v2-bf16

from ByteDance/Bernini-Diffusers-v2
bf16
Image to video · ByteDance ↓ 50 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-08-18

Bio-Medical-Llama-3-8B-4bit

from ContactDoctor/Bio-Medical-Llama-3-8B
4-bit
Text generation · ContactDoctor ↓ 50 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

other · updated 2025-06-03

Falcon-H1R-7B-6bit

from tiiuae/Falcon-H1R-7B
6-bit
Text generation · TII · Falcon ↓ 50 · ♥ 0
Params
7.6B
Weights
≈ 6.2 GB
Mac memory
16 GB+

falcon-llm-license · updated 2026-01-05

Fara1.5-4B-8bit

from microsoft/Fara1.5-4B
8-bit
Vision + text · Microsoft · Phi ↓ 50 · ♥ 0
Params
4.5B
Weights
≈ 5.1 GB
Mac memory
8 GB+

mit · updated 2026-08-04

HY-MT1.5-7B-8bit

from tencent/HY-MT1.5-7B
8-bit
Text generation · tencent ↓ 50 · ♥ 0
Params
7.5B
Weights
≈ 8.0 GB
Mac memory
16 GB+

updated 2026-01-03

Huihui-gemma-3-270m-it-abliterated-4bit

from huihui-ai/Huihui-gemma-3-270m-it-abliterated
4-bit
Text generation · huihui-ai ↓ 50 · ♥ 0
Params
268M
Weights
≈ 151 MB
Mac memory
8 GB+

gemma · updated 2025-09-27

Llama-3.1-Tulu-3-70B-6bit

from allenai/Llama-3.1-Tulu-3-70B
6-bit
Text generation · Ai2 · OLMo ↓ 50 · ♥ 0
Params
71B
Weights
≈ 57.3 GB
Mac memory
96 GB+

llama3.1 · updated 2024-11-25

Mellum-4b-sft-python-8bit

from JetBrains/Mellum-4b-sft-python
8-bit
Text generation · JetBrains ↓ 50 · ♥ 0
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-28

Meta-Llama-3.1-8B-8bit

mlx-community/Meta-Llama-3.1-8B-8bit
8-bit
Text generation ↓ 50 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.1 · updated 2024-07-23

Ming-omni-tts-16.8B-A3B-4bit

mlx-community/Ming-omni-tts-16.8B-A3B-4bit
4-bit
Uncategorised ↓ 50 · ♥ 0
Params
18B
Weights
≈ 2.4 GB
Mac memory
8 GB+

updated 2026-03-06

Mistral-Small-3.1-24B-Instruct-2503-6bit

from mistralai/Mistral-Small-3.1-24B-Base-2503
6-bit
Uncategorised · Mistral ↓ 50 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-03-19

MolmoPoint-8B-nvfp4

from Qwen/Qwen3-8B
4-bit
Vision + text · Qwen ↓ 50 · ♥ 0
Params
8.7B
Weights
≈ 7.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-21

OLMo-2-1124-13B-Instruct-6bit

from allenai/OLMo-2-1124-13B-Instruct
6-bit
Text generation · Ai2 · OLMo ↓ 50 · ♥ 0
Params
14B
Weights
≈ 11.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-11-27

Qwen2.5-3B-bf16

mlx-community/Qwen2.5-3B-bf16
bf16
Text generation ↓ 50 · ♥ 0
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

qwen-research · updated 2024-09-18

Seed-Coder-8B-Reasoning-bf16-mlx-8Bit

from ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16
8-bit
Text generation · ByteDance-Seed ↓ 50 · ♥ 0
Params
8.3B
Weights
≈ 8.8 GB
Mac memory
16 GB+

mit · updated 2025-07-18

Step-Audio-EditX-bf16

from stepfun-ai/Step-Audio-EditX
bf16
Audio to audio · stepfun-ai ↓ 50 · ♥ 0
Params
3.5B
Weights
≈ 7.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-10-07

YandexGPT-5-Lite-8B-instruct-4bit

from yandex/YandexGPT-5-Lite-8B-instruct
4-bit
Uncategorised · yandex ↓ 50 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

yandexgpt-5-lite-8b · updated 2025-05-24

granite-3b-code-instruct-8bit

from ibm-granite/granite-3b-code-base-2k
8-bit
Text generation · IBM · Granite ↓ 50 · ♥ 0
Params
3.5B
Weights
≈ 3.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2024-05-06

llm-jp-3-3.7b-instruct

mlx-community/llm-jp-3-3.7b-instruct
Text generation ↓ 50 · ♥ 0
Params
3.8B
Weights
≈ 7.6 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-09-25

llm-jp-3.1-13b-instruct4-8bit

from llm-jp/llm-jp-3.1-13b-instruct4
8-bit
Text generation · llm-jp ↓ 50 · ♥ 0
Params
14B
Weights
≈ 14.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-16

Lance-3B-bf16

from bytedance-research/Lance
bf16
Image to image · bytedance-research ↓ 49 · ♥ 9
Params
6.2B
Weights
≈ 12.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-06-05

Ornith-1.0-35B-6bit

from ornith-ai/Ornith-1.0-35B
6-bit
Vision + text · ornith-ai ↓ 49 · ♥ 7
Params
35B
Weights
≈ 29.1 GB
Mac memory
48 GB+

mit · updated 2026-06-27

Ornith-1.0-35B-3bit

from ornith-ai/Ornith-1.0-35B
3-bit
Vision + text · ornith-ai ↓ 49 · ♥ 3
Params
35B
Weights
≈ 16.1 GB
Mac memory
24 GB+

mit · updated 2026-06-27

DeepCoder-14B-Preview-4bit

from agentica-org/DeepCoder-14B-Preview
4-bit
Text generation · agentica-org ↓ 49 · ♥ 2
Params
15B
Weights
≈ 8.3 GB
Mac memory
16 GB+

mit · updated 2025-04-08

Laguna-XS.2-mxfp8

from poolside/Laguna-XS.2
MXFP8
Text generation · poolside ↓ 49 · ♥ 2
Params
33B
Weights
≈ 35.5 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-04-28

Qwen3-VL-32B-Thinking-4bit

mlx-community/Qwen3-VL-32B-Thinking-4bit
4-bit
Vision + text ↓ 49 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-10-21

ERNIE-4.5-21B-A3B-PT-5bit

from baidu/ERNIE-4.5-21B-A3B-PT
5-bit
Text generation · baidu ↓ 49 · ♥ 1
Params
22B
Weights
≈ 15.0 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-07-04

Falcon-E-3B-Instruct-1.58bit

from tiiuae/Falcon-E-3B-Instruct
58-bit
Text generation · TII · Falcon ↓ 49 · ♥ 1
Params
864M
Weights
≈ 999 MB
Mac memory
8 GB+

falcon-llm-license · updated 2025-06-10

JOSIE-TinyLlama-1.1B-32k-base-4bit

from Doctor-Shotgun/TinyLlama-1.1B-32k
4-bit
Text generation · Doctor-Shotgun ↓ 49 · ♥ 1
Params
1.1B
Weights
≈ 619 MB
Mac memory
8 GB+

updated 2024-05-24

Josiefied-Qwen3-1.7B-abliterated-v1-bf16

from Goekdeniz-Guelmez/Josiefied-Qwen3-1.7B-abliterated-v1
bf16
Text generation · Goekdeniz-Guelmez ↓ 49 · ♥ 1
Params
1.7B
Weights
≈ 3.4 GB
Mac memory
8 GB+

updated 2025-04-29

Maxine-34B-stock

from louisbrulenaudet/Maxine-34B-stock
Text generation · louisbrulenaudet ↓ 49 · ♥ 1
Params
34B
Weights
≈ 137 GB
Mac memory
192 GB+

updated 2024-07-10

Mega-ASR-8bit

from Qwen/Qwen3-ASR-1.7B
8-bit
Speech recognition · Qwen ↓ 49 · ♥ 1
Params
2.0B
Weights
≈ 2.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-23

Mixtral-8x7B-Instruct-v0.1-8bit

mlx-community/Mixtral-8x7B-Instruct-v0.1-8bit
8-bit
Uncategorised ↓ 49 · ♥ 1
Params
47B
Weights
≈ 49.6 GB
Mac memory
64 GB+

apache-2.0 · updated 2024-05-10

Qwen3.6-27B-MTP-5bit

from Qwen/Qwen3.6-27B
5-bit
Text generation · Qwen ↓ 49 · ♥ 1
Params
425M
Weights
≈ 292 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-06-01

3b-fr-ft-research_release-4bit

from canopylabs/orpheus-3b-0.1-pretrained
4-bit
Text to speech · canopylabs ↓ 49 · ♥ 0
Params
3.3B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-09

Agents-A1-3bit

from InternScience/Agents-A1
3-bit
Vision + text · InternScience ↓ 49 · ♥ 0
Params
35B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-01

EXAONE-Deep-7.8B-4bit

from LGAI-EXAONE/EXAONE-Deep-7.8B
4-bit
Text generation · LGAI-EXAONE ↓ 49 · ♥ 0
Params
7.8B
Weights
≈ 4.4 GB
Mac memory
8 GB+

exaone · updated 2025-03-18

GLM-4-32B-Base-0414-8bit

from zai-org/GLM-4-32B-Base-0414
8-bit
Text generation · zai-org ↓ 49 · ♥ 0
Params
33B
Weights
≈ 34.6 GB
Mac memory
48 GB+

mit · updated 2025-04-21

Llama-3.1-Swallow-70B-Instruct-v0.3-8bit

from tokyotech-llm/Llama-3.1-Swallow-70B-Instruct-v0.3
8-bit
Text generation · tokyotech-llm ↓ 49 · ♥ 0
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.1 · updated 2025-03-10

Metric-Video-Depth-Anything-Small-MLX

mlx-community/Metric-Video-Depth-Anything-Small-MLX
Depth estimation ↓ 49 · ♥ 0
Params
29M
Weights
≈ 116 MB
Mac memory
8 GB+

cc-by-nc-4.0 · updated 2026-09-01

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-5bit

from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
5-bit
Vision + text · NVIDIA ↓ 49 · ♥ 0
Params
33B
Weights
≈ 23.7 GB
Mac memory
32 GB+

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

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-6bit

from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16
6-bit
Vision + text · NVIDIA ↓ 49 · ♥ 0
Params
33B
Weights
≈ 27.7 GB
Mac memory
48 GB+

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

North-Micro-Vision-Instruct-8bit

from CohereLabs/North-Micro-Vision-Instruct
8-bit
Vision + text · Cohere ↓ 49 · ♥ 0
Params
2.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Qwen2-72B-Instruct-unquantized

mlx-community/Qwen2-72B-Instruct-unquantized
Text generation ↓ 49 · ♥ 0
Params
73B
Weights
≈ 145 GB
Mac memory
192 GB+

tongyi-qianwen · updated 2024-06-07

RakutenAI-2.0-8x7B-MLX-4bit

from Rakuten/RakutenAI-2.0-8x7B
4-bit
Text generation · Rakuten ↓ 49 · ♥ 0
Params
47B
Weights
≈ 26.3 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-03-20

SongGeneration-v2-large-bf16

from tencent/SongGeneration
bf16
Text to audio · tencent ↓ 49 · ♥ 0
Params
5.1B
Weights
≈ 10.2 GB
Mac memory
16 GB+

other · updated 2026-05-31

SongGeneration-v2-medium-fp32

from tencent/SongGeneration
fp32
Text to audio · tencent ↓ 49 · ♥ 0
Params
2.8B
Weights
≈ 11.2 GB
Mac memory
16 GB+

other · updated 2026-05-31

Step-3.7-Flash-oQ2e

from stepfun-ai/Step-3.7-Flash
2-bit
Vision + text · stepfun-ai ↓ 49 · ♥ 0
Params
199B
Weights
≈ 62.6 GB
Mac memory
96 GB+

apache-2.0 · updated 2026-07-19

Yi-6B-Chat-8bit

from 01-ai/Yi-6B-Chat
8-bit
Text generation · 01.AI · Yi ↓ 49 · ♥ 0
Params
6.1B
Weights
≈ 6.4 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-11-05

gemma-3-4b-pt-6bit

mlx-community/gemma-3-4b-pt-6bit
6-bit
Vision + text ↓ 49 · ♥ 0
Params
5.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

gemma · updated 2025-03-18

gemma-4-26B-A4B-it-qat-assistant-5bit

from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
5-bit
Text generation · Google · Gemma ↓ 49 · ♥ 0
Params
420M
Weights
≈ 289 MB
Mac memory
8 GB+

gemma · updated 2026-06-05