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 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

5,842 builds · page 65 of 98

InternVL3-38B-8bit

from OpenGVLab/InternVL3-1B-Instruct
8-bit
Vision + text · OpenGVLab ↓ 36 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-30

InternVL3-8B-3bit

from OpenGVLab/InternVL3-1B-Instruct
3-bit
Vision + text · OpenGVLab ↓ 36 · ♥ 0
Params
7.9B
Weights
≈ 4.0 GB
Mac memory
8 GB+

qwen · updated 2025-04-18

Ministral-3-3B-Reasoning-2512-5bit

from mistralai/Ministral-3-3B-Base-2512
5-bit
Uncategorised · Mistral ↓ 36 · ♥ 0
Params
3.8B
Weights
≈ 3.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-03

NemotronLabs-VoiceChat-11B-bf16

from nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
bf16
Uncategorised · NVIDIA ↓ 36 · ♥ 0
Params
11B
Weights
≈ 22.2 GB
Mac memory
32 GB+

openmdw-1.1 · updated 2026-08-08

North-Micro-Vision-Instruct-5bit

from CohereLabs/North-Micro-Vision-Instruct
5-bit
Vision + text · Cohere ↓ 36 · ♥ 0
Params
2.5B
Weights
≈ 2.4 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-12

Nous-Hermes-2-Mixtral-8x7B-DPO-8bit

from mistralai/Mixtral-8x7B-v0.1
8-bit
Uncategorised · Mistral ↓ 36 · ♥ 0
Params
47B
Weights
≈ 49.6 GB
Mac memory
64 GB+

apache-2.0 · updated 2024-04-27

Olmo-3-1025-7B-4bit

from allenai/Olmo-3-1025-7B
4-bit
Text generation · Ai2 · OLMo ↓ 36 · ♥ 0
Params
7.3B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-11-21

QwQ-Coder-instruct-mlx-4Bit

from YOYO-AI/QwQ-Coder-instruct
4-bit
Text generation · YOYO-AI ↓ 36 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-20

Qwen1.5-32B-8bit

mlx-community/Qwen1.5-32B-8bit
8-bit
Text generation ↓ 36 · ♥ 0
Params
33B
Weights
≈ 35.3 GB
Mac memory
48 GB+

tongyi-qianwen-research · updated 2024-04-05

Ring-mini-2.0-8bit

from inclusionAI/Ring-mini-2.0
8-bit
Text generation · inclusionAI ↓ 36 · ♥ 0
Params
16B
Weights
≈ 17.3 GB
Mac memory
24 GB+

mit · updated 2025-09-15

SakanaAI-EvoLLM-JP-v1-7B-8bit

from SakanaAI/EvoLLM-JP-v1-7B
8-bit
Text generation · SakanaAI ↓ 36 · ♥ 0
Params
7.2B
Weights
≈ 7.7 GB
Mac memory
16 GB+

other · updated 2024-10-23

UI-Venus-1.5-8B-6bit

from inclusionAI/UI-Venus-1.5-8B
6-bit
Vision + text · inclusionAI ↓ 36 · ♥ 0
Params
8.8B
Weights
≈ 7.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-20

YOLO26m-OptiQ-6bit

from Ultralytics/YOLO26
6-bit
Object detection · Ultralytics ↓ 36 · ♥ 0
Params
—
Weights
—
Mac memory
—

agpl-3.0 · updated 2026-09-28

aya-vision-8b-bf16

mlx-community/aya-vision-8b-bf16
bf16
Vision + text ↓ 36 · ♥ 0
Params
8.6B
Weights
≈ 17.3 GB
Mac memory
24 GB+

cc-by-nc-4.0 · updated 2025-03-05

dolphin-2.9.3-qwen2-0.5b-2bit

from Qwen/Qwen2-0.5B
2-bit
Uncategorised · Qwen ↓ 36 · ♥ 0
Params
46M
Weights
≈ 41 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-14

dots.mocr-6bit

from dots-studio/dots.mocr
6-bit
Vision + text · dots-studio ↓ 36 · ♥ 0
Params
3.0B
Weights
≈ 4.0 GB
Mac memory
8 GB+

mit · updated 2026-04-03

dots.ocr-mxfp4

mlx-community/dots.ocr-mxfp4
MXFP4
Vision + text ↓ 36 · ♥ 0
Params
3.0B
Weights
≈ 3.5 GB
Mac memory
8 GB+

mit · updated 2026-02-17

functiongemma-270m-it-5bit

from google/functiongemma-270m-it
5-bit
Text generation · Google · Gemma ↓ 36 · ♥ 0
Params
268M
Weights
≈ 184 MB
Mac memory
8 GB+

gemma · updated 2025-12-18

gemma-4-E2B-it-qat-bf16

mlx-community/gemma-4-E2B-it-qat-bf16
bf16
Vision + text ↓ 36 · ♥ 0
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
Vision + text · Qwen ↓ 36 · ♥ 0
Params
8.3B
Weights
≈ 16.6 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-09-17

kanana-2-3b-instruct-6bit

from kakaocorp/kanana-2-3b-instruct
6-bit
Text generation · kakaocorp ↓ 36 · ♥ 0
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

kanana-open-license · updated 2026-08-06

lift-oQ4

from datalab-to/lift
4-bit
Vision + text · datalab-to ↓ 36 · ♥ 0
Params
9.4B
Weights
≈ 6.0 GB
Mac memory
16 GB+

openrail · updated 2026-06-27

phi-4-abliterated-8bit

from huihui-ai/phi-4-abliterated
8-bit
Text generation · huihui-ai ↓ 36 · ♥ 0
Params
15B
Weights
≈ 15.6 GB
Mac memory
24 GB+

mit · updated 2025-01-09

whisper-small.en-4bit

from openai/whisper-small.en
4-bit
Speech recognition · OpenAI · gpt-oss ↓ 36 · ♥ 0
Params
241M
Weights
≈ 139 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

watt-tool-8B

from watt-ai/watt-tool-8B
4-bit
Uncategorised · watt-ai ↓ 35 · ♥ 4
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-02-13

LFM2-1.2B-bf16

from LiquidAI/LFM2-1.2B
bf16
Text generation · LiquidAI ↓ 35 · ♥ 2
Params
1.2B
Weights
≈ 2.3 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-07-11

SciPhi-Triplex-4bit

from SciPhi/Triplex
4-bit
Text generation · SciPhi ↓ 35 · ♥ 2
Params
3.8B
Weights
≈ 2.1 GB
Mac memory
8 GB+

cc-by-nc-sa-4.0 · updated 2026-06-26

dolphin-2.9.4-gemma2-2b-4bit

from google/gemma-2-2b
4-bit
Uncategorised · Google · Gemma ↓ 35 · ♥ 2
Params
2.6B
Weights
≈ 1.5 GB
Mac memory
8 GB+

gemma · updated 2024-08-30

gemma-3-27b-pt-bf16

mlx-community/gemma-3-27b-pt-bf16
bf16
Vision + text ↓ 35 · ♥ 2
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-03-18

CAT-Thinking-8B-MLX-8bit

from cyberagent/CAT-Thinking-8B
8-bit
Text generation · cyberagent ↓ 35 · ♥ 1
Params
8.2B
Weights
≈ 8.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-06-03

HY-MT1.5-7B-bf16

from tencent/HY-MT1.5-7B
bf16
Text generation · tencent ↓ 35 · ♥ 1
Params
7.5B
Weights
≈ 15.0 GB
Mac memory
24 GB+

updated 2026-01-03

Kumru-2B-bf16

from vngrs-ai/Kumru-2B
bf16
Text generation · vngrs-ai ↓ 35 · ♥ 1
Params
2.4B
Weights
≈ 4.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-15

LFM2-2.6B-Exp-bf16

from LiquidAI/LFM2-2.6B-Exp
bf16
Text generation · LiquidAI ↓ 35 · ♥ 1
Params
2.6B
Weights
≈ 5.1 GB
Mac memory
8 GB+

lfm1.0 · updated 2025-12-26

Qwen1.5-110B-4bit

mlx-community/Qwen1.5-110B-4bit
4-bit
Text generation ↓ 35 · ♥ 1
Params
111B
Weights
≈ 62.6 GB
Mac memory
96 GB+

tongyi-qianwen · updated 2024-04-26

Qwen2-VL-7B-8bit

mlx-community/Qwen2-VL-7B-8bit
8-bit
Vision + text ↓ 35 · ♥ 1
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
4-bit
Vision + text ↓ 35 · ♥ 1
Params
12B
Weights
≈ 21.3 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-03-05

Ring-flash-linear-2.0-128k-4bit

from inclusionAI/Ring-flash-linear-2.0-128k
4-bit
Text generation · inclusionAI ↓ 35 · ♥ 1
Params
104B
Weights
≈ 58.6 GB
Mac memory
96 GB+

mit · updated 2025-10-23

SmolLM-360M-Instruct-fp16

mlx-community/SmolLM-360M-Instruct-fp16
fp16
Text generation ↓ 35 · ♥ 1
Params
362M
Weights
≈ 724 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-07-16

Swallow-7b-instruct-v0.1-4bit

mlx-community/Swallow-7b-instruct-v0.1-4bit
4-bit
Text generation ↓ 35 · ♥ 1
Params
6.8B
Weights
≈ 4.1 GB
Mac memory
8 GB+

llama2 · updated 2024-04-27

cogito-v2-preview-llama-70B-4Bit

from deepcogito/cogito-v2-preview-llama-70B
4-bit
Text generation · deepcogito ↓ 35 · ♥ 1
Params
71B
Weights
≈ 39.7 GB
Mac memory
48 GB+

llama3.1 · updated 2025-07-31

dolphin-2.9.4-llama3.1-8b

from dphn/dolphin-2.9.4-llama3.1-8b
Uncategorised · dphn ↓ 35 · ♥ 1
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.1 · updated 2024-10-21

granite-4.0-h-1b-8bit

from ibm-granite/granite-4.0-h-1b
8-bit
Text generation · IBM · Granite ↓ 35 · ♥ 1
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

llava-interleave-qwen-0.5b-8bit

mlx-community/llava-interleave-qwen-0.5b-8bit
8-bit
Vision + text ↓ 35 · ♥ 1
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
6-bit
Vision + text ↓ 35 · ♥ 1
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
4-bit
Vision + text ↓ 35 · ♥ 1
Params
3.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

gemma · updated 2025-02-19

salamandra-7b-instruct-mlx-bf16

from BSC-LT/salamandra-7b-instruct
bf16
Text generation · BSC-LT ↓ 35 · ♥ 1
Params
7.8B
Weights
≈ 15.5 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-08-21

simplescaling-s1.1-32B-8bit

from simplescaling/s1.1-32B
8-bit
Text generation · simplescaling ↓ 35 · ♥ 1
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-02-16

3b-zh-ft-research_release-8bit

from canopylabs/orpheus-3b-0.1-pretrained
8-bit
Text to speech · canopylabs ↓ 35 · ♥ 0
Params
3.3B
Weights
≈ 3.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-09

Cydonia-24B-v3-6bit

from TheDrummer/Cydonia-24B-v3
6-bit
Text generation · TheDrummer ↓ 35 · ♥ 0
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+

other · updated 2025-06-04

DeepFloyd-t5-v1_1-xxl

mlx-community/DeepFloyd-t5-v1_1-xxl
Uncategorised ↓ 35 · ♥ 0
Params
4.8B
Weights
≈ 9.5 GB
Mac memory
16 GB+

other · updated 2024-08-01

DeepScaleR-1.5B-Preview-4bit

from agentica-org/DeepScaleR-1.5B-Preview
4-bit
Text generation · agentica-org ↓ 35 · ♥ 0
Params
1.8B
Weights
≈ 1000 MB
Mac memory
8 GB+

mit · updated 2025-02-14

EuroLLM-22B-Instruct-2512-mlx-bf16

from utter-project/EuroLLM-22B-Instruct-2512
bf16
Text generation · utter-project ↓ 35 · ♥ 0
Params
23B
Weights
≈ 45.3 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-12-16

Falcon3-10B-Instruct-1.58bit-8bit

from tiiuae/Falcon3-10B-Instruct-1.58bit
58-bit
Text generation · TII · Falcon ↓ 35 · ♥ 0
Params
2.6B
Weights
≈ 3.2 GB
Mac memory
8 GB+

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

Falcon3-3B-Instruct-1.58bit-4bit

from tiiuae/Falcon3-3B-Instruct-1.58bit
58-bit
Text generation · TII · Falcon ↓ 35 · ♥ 0
Params
1.3B
Weights
≈ 1.7 GB
Mac memory
8 GB+

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

Fara-7B-4bit

from microsoft/Fara-7B
4-bit
Vision + text · Microsoft · Phi ↓ 35 · ♥ 0
Params
8.3B
Weights
≈ 5.6 GB
Mac memory
16 GB+

mit · updated 2026-07-31