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 15m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

5,842 builds · page 77 of 98

Polaris-4B-Preview-5bit

from POLARIS-Project/Polaris-4B-Preview
5-bit
Text generation · POLARIS-Project ↓ 27 · ♥ 0
Params
4.0B
Weights
≈ 2.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-03

QwQ-0.5B-4bit

from InfiniAILab/QwQ-0.5B
4-bit
Text generation · InfiniAILab ↓ 27 · ♥ 0
Params
494M
Weights
≈ 278 MB
Mac memory
8 GB+

updated 2025-04-07

Qwen2-Math-7B-Instruct-8bit

mlx-community/Qwen2-Math-7B-Instruct-8bit
8-bit
Text generation ↓ 27 · ♥ 0
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-08-09

Qwen3.5-2B-mixed_4_8

mlx-community/Qwen3.5-2B-mixed_4_8
4-bit
Uncategorised ↓ 27 · ♥ 0
Params
709M
Weights
≈ 960 MB
Mac memory
8 GB+

updated 2026-03-02

RakutenAI-7B-MLX-4bit

from Rakuten/RakutenAI-7B
4-bit
Text generation · Rakuten ↓ 27 · ♥ 0
Params
7.4B
Weights
≈ 4.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-20

RakutenAI-7B-chat-MLX-4bit

from Rakuten/RakutenAI-7B-chat
4-bit
Text generation · Rakuten ↓ 27 · ♥ 0
Params
7.4B
Weights
≈ 4.1 GB
Mac memory
8 GB+

updated 2026-03-20

Ring-mini-linear-2.0-8bit

from inclusionAI/Ring-mini-linear-2.0
8-bit
Text generation · inclusionAI ↓ 27 · ♥ 0
Params
16B
Weights
≈ 17.5 GB
Mac memory
24 GB+

mit · updated 2025-11-02

Tess-4-27B-mxfp4

from migtissera/Tess-4-27B
MXFP4
Vision + text · migtissera ↓ 27 · ♥ 0
Params
27B
Weights
≈ 16.1 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-07-10

Tessa-T1-32B-mlx-4bit

from Tesslate/Tessa-T1-32B
4-bit
Text generation · Tesslate ↓ 27 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-25

Tessa-T1-3B-mlx-bf16

from Tesslate/Tessa-T1-3B
bf16
Text generation · Tesslate ↓ 27 · ♥ 0
Params
3.1B
Weights
≈ 6.2 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-25

Tmax-9B-MLX-6bit

from allenai/tmax-9b
6-bit
Text generation · Ai2 · OLMo ↓ 27 · ♥ 0
Params
9.0B
Weights
≈ 7.3 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-06-25

UI-TARS-72B-DPO-4bit

mlx-community/UI-TARS-72B-DPO-4bit
4-bit
Vision + text ↓ 27 · ♥ 0
Params
73B
Weights
≈ 42.3 GB
Mac memory
64 GB+

apache-2.0 · updated 2025-03-06

VL-Rethinker-72B-4bit

from Qwen/Qwen2.5-VL-7B-Instruct
4-bit
Visual question answering · Qwen ↓ 27 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-04-16

Virtuoso-Medium-v2-6bit

from arcee-ai/Virtuoso-Medium-v2
6-bit
Text generation · arcee-ai ↓ 27 · ♥ 0
Params
33B
Weights
≈ 26.6 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-01-30

deepcogito-cogito-v1-preview-llama-3B-6bit

from deepcogito/cogito-v1-preview-llama-3B
6-bit
Text generation · deepcogito ↓ 27 · ♥ 0
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

llama3.2 · updated 2025-04-08

deepcogito-cogito-v1-preview-llama-3B-8bit

from deepcogito/cogito-v1-preview-llama-3B
8-bit
Text generation · deepcogito ↓ 27 · ♥ 0
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+

llama3.2 · updated 2025-04-08

dolphin-2.6-mistral-7b-dpo-laser-mlx

mlx-community/dolphin-2.6-mistral-7b-dpo-laser-mlx
Uncategorised ↓ 27 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-01-14

dolphin-2.9.1-mixtral-1x22b-4bit

from mistral-community/Mixtral-8x22B-v0.1
4-bit
Uncategorised · mistral-community ↓ 27 · ♥ 0
Params
22B
Weights
≈ 12.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-05-22

gemma-2-2b-fp16

mlx-community/gemma-2-2b-fp16
fp16
Text generation ↓ 27 · ♥ 0
Params
2.6B
Weights
≈ 5.2 GB
Mac memory
8 GB+

gemma · updated 2024-07-31

gemma-2-9b-it-SimPO

from google/gemma-2-9b-it
Uncategorised · Google · Gemma ↓ 27 · ♥ 0
Params
9.2B
Weights
≈ 18.5 GB
Mac memory
24 GB+

mit · updated 2024-09-18

gemma-3-270m-qat-6bit

from google/gemma-3-270m-qat
6-bit
Text generation · Google · Gemma ↓ 27 · ♥ 0
Params
436M
Weights
≈ 354 MB
Mac memory
8 GB+

gemma · updated 2025-08-09

gemma-3n-E2B-6bit

from google/gemma-3n-E4B
6-bit
Vision + text · Google · Gemma ↓ 27 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

gemma-3n-E2B-it-6bit

from google/gemma-3n-E4B-it
6-bit
Vision + text · Google · Gemma ↓ 27 · ♥ 0
Params
—
Weights
—
Mac memory
—

gemma · updated 2025-07-12

gemma-3n-E4B-it-3bit

from google/gemma-3n-E4B
3-bit
Vision + text · Google · Gemma ↓ 27 · ♥ 0
Params
7.8B
Weights
≈ 5.0 GB
Mac memory
8 GB+

gemma · updated 2025-07-06

granite-4.0-h-1b-3bit

from ibm-granite/granite-4.0-h-1b
3-bit
Text generation · IBM · Granite ↓ 27 · ♥ 0
Params
1.5B
Weights
≈ 641 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

olmOCR-7B-0225-preview-6bit

from Qwen/Qwen2-VL-7B-Instruct
6-bit
Vision + text · Qwen ↓ 27 · ♥ 0
Params
8.3B
Weights
≈ 7.5 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-03-03

paligemma2-28b-mix-224-8bit

mlx-community/paligemma2-28b-mix-224-8bit
8-bit
Vision + text ↓ 27 · ♥ 0
Params
28B
Weights
≈ 29.8 GB
Mac memory
48 GB+

gemma · updated 2025-02-20

paligemma2-3b-mix-448-8bit

mlx-community/paligemma2-3b-mix-448-8bit
8-bit
Vision + text ↓ 27 · ♥ 0
Params
3.0B
Weights
≈ 3.6 GB
Mac memory
8 GB+

gemma · updated 2025-02-19

parler-tts-mini

mlx-community/parler-tts-mini
Text to speech ↓ 27 · ♥ 0
Params
956M
Weights
≈ 3.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-04

sapiens2-normal-1b-bf16

from facebook/sapiens2-normal-1b
bf16
Depth estimation · facebook ↓ 27 · ♥ 0
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

sapiens2-license · updated 2026-09-13

sapiens2-pose-1b-bf16

from facebook/sapiens2-pose-1b
bf16
Keypoint detection · facebook ↓ 27 · ♥ 0
Params
1.5B
Weights
≈ 3.0 GB
Mac memory
8 GB+

sapiens2-license · updated 2026-09-13

sapiens2-seg-0.4b-mxfp8

from facebook/sapiens2-seg-0.4b
MXFP8
Image to image · facebook ↓ 27 · ♥ 0
Params
407M
Weights
≈ 468 MB
Mac memory
8 GB+

sapiens2-license · updated 2026-04-24

shisa-v2-llama3.3-70b-8bit

from shisa-ai/shisa-v2-llama3.3-70b
8-bit
Text generation · shisa-ai ↓ 27 · ♥ 0
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.3 · updated 2025-04-15

typhoon-v1.5-8b-instruct-4bit-mlx

mlx-community/typhoon-v1.5-8b-instruct-4bit-mlx
4-bit
Text generation ↓ 27 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3 · updated 2024-05-09

unsloth-granite-4.1-8b-mlx-oQ6

from unsloth/granite-4.1-8b
6-bit
Uncategorised · unsloth ↓ 27 · ♥ 0
Params
8.8B
Weights
≈ 7.1 GB
Mac memory
16 GB+

updated 2026-05-04

whisper-base-8bit

from openai/whisper-base
8-bit
Speech recognition · OpenAI · gpt-oss ↓ 27 · ♥ 0
Params
72M
Weights
≈ 77 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-small.en-fp16

from openai/whisper-small.en
fp16
Speech recognition · OpenAI · gpt-oss ↓ 27 · ♥ 0
Params
241M
Weights
≈ 481 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-tiny.en-mlx-8bit

mlx-community/whisper-tiny.en-mlx-8bit
8-bit
Uncategorised ↓ 27 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

Llama-OuteTTS-1.0-1B-fp16

mlx-community/Llama-OuteTTS-1.0-1B-fp16
fp16
Text to speech ↓ 26 · ♥ 3
Params
1.2B
Weights
≈ 2.5 GB
Mac memory
8 GB+

cc-by-nc-sa-4.0 · updated 2025-05-19

Qwen3-235B-A22B-mixed-3-6bit

from Qwen/Qwen3-235B-A22B
6-bit
Text generation · Qwen ↓ 26 · ♥ 2
Params
235B
Weights
≈ 191 GB
Mac memory
256 GB+

apache-2.0 · updated 2025-05-09

dolphin-2.9.3-qwen2-1.5b-2bit

from Qwen/Qwen2-1.5B
2-bit
Uncategorised · Qwen ↓ 26 · ♥ 2
Params
145M
Weights
≈ 127 MB
Mac memory
8 GB+

apache-2.0 · updated 2024-06-14

gemma-4-31b-5bit

from google/gemma-4-31b
5-bit
Vision + text · Google · Gemma ↓ 26 · ♥ 2
Params
31B
Weights
≈ 22.2 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-02

LFM2-350M-5bit

from LiquidAI/LFM2-350M
5-bit
Text generation · LiquidAI ↓ 26 · ♥ 1
Params
354M
Weights
≈ 244 MB
Mac memory
8 GB+

lfm1.0 · updated 2025-07-11

Mega-ASR-6bit

from Qwen/Qwen3-ASR-1.7B
6-bit
Speech recognition · Qwen ↓ 26 · ♥ 1
Params
2.0B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-23

MiniCPM-2B-dpo-bf16-4bit

mlx-community/MiniCPM-2B-dpo-bf16-4bit
4-bit
Uncategorised ↓ 26 · ♥ 1
Params
3.0B
Weights
≈ 1.7 GB
Mac memory
8 GB+

updated 2024-05-06

dolphin-2.9.1-qwen-110b-2bit

from Qwen/Qwen1.5-110B
2-bit
Uncategorised · Qwen ↓ 26 · ♥ 1
Params
111B
Weights
≈ 34.8 GB
Mac memory
48 GB+

other · updated 2024-05-12

granite-4.0-350m-base-8bit

from ibm-granite/granite-4.0-350m-base
8-bit
Text generation · IBM · Granite ↓ 26 · ♥ 1
Params
352M
Weights
≈ 374 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

omost-dolphin-2.9-llama3-8b-mlx-8bit

mlx-community/omost-dolphin-2.9-llama3-8b-mlx-8bit
8-bit
Uncategorised ↓ 26 · ♥ 1
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

updated 2024-06-08

phi-2-orange-v2

mlx-community/phi-2-orange-v2
Uncategorised ↓ 26 · ♥ 1
Params
2.8B
Weights
≈ 10.9 GB
Mac memory
16 GB+

mit · updated 2024-04-11

3b-hi-ft-research_release-6bit

from canopylabs/orpheus-3b-0.1-pretrained
6-bit
Text to speech · canopylabs ↓ 26 · ♥ 0
Params
3.3B
Weights
≈ 2.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-09

Arcee-Blitz-8bit

from arcee-ai/Arcee-Blitz
8-bit
Text generation · arcee-ai ↓ 26 · ♥ 0
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-06-03

ArrowCanaria-Llama-8B-SFT-v0.1-MLX-8bit

from DataPilot/ArrowCanaria-Llama-8B-SFT-v0.1
8-bit
Text generation · DataPilot ↓ 26 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3.3 · updated 2026-03-27

Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-4bit

from SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B
4-bit
Text generation · SentientAGI ↓ 26 · ♥ 0
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama3.1 · updated 2025-06-11

Dobby-Mini-Unhinged-Plus-Llama-3.1-8B-bf16

from SentientAGI/Dobby-Mini-Unhinged-Plus-Llama-3.1-8B
bf16
Text generation · SentientAGI ↓ 26 · ♥ 0
Params
8.0B
Weights
≈ 16.1 GB
Mac memory
24 GB+

llama3.1 · updated 2025-06-11

EXAONE-Deep-2.4B-8bit

from LGAI-EXAONE/EXAONE-Deep-2.4B
8-bit
Text generation · LGAI-EXAONE ↓ 26 · ♥ 0
Params
2.4B
Weights
≈ 2.6 GB
Mac memory
8 GB+

exaone · updated 2025-03-18

EXAONE-Deep-32B-3bit

from LGAI-EXAONE/EXAONE-Deep-32B
3-bit
Text generation · LGAI-EXAONE ↓ 26 · ♥ 0
Params
32B
Weights
≈ 14.0 GB
Mac memory
24 GB+

exaone · updated 2025-03-18

Falcon-H1-Tiny-90M-Base-5bit

from tiiuae/Falcon-H1-Tiny-90M-Base
5-bit
Text generation · TII · Falcon ↓ 26 · ♥ 0
Params
91M
Weights
≈ 63 MB
Mac memory
8 GB+

falcon-llm-license · updated 2026-01-28