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 75 of 98

paligemma2-3b-mix-224-bf16

mlx-community/paligemma2-3b-mix-224-bf16
bf16
Vision + text ↓ 29 · ♥ 0
Params
3.0B
Weights
≈ 6.1 GB
Mac memory
16 GB+

gemma · updated 2025-02-19

royallab_MN-LooseCannon-12B-v2

from royallab/MN-LooseCannon-12B-v2
8-bit
Text generation · royallab ↓ 29 · ♥ 0
Params
12B
Weights
≈ 13.0 GB
Mac memory
24 GB+

updated 2024-10-12

shisa-v2.1-unphi4-14b-mlx-8bit

from shisa-ai/shisa-v2.1-unphi4-14b
8-bit
Text generation · shisa-ai ↓ 29 · ♥ 0
Params
15B
Weights
≈ 15.6 GB
Mac memory
24 GB+

mit · updated 2025-12-16

simplescaling-s1.1-32B-4bit

from simplescaling/s1.1-32B
4-bit
Text generation · simplescaling ↓ 29 · ♥ 0
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-02-16

unsloth-granite-4.1-8b-mlx-oQ8

from unsloth/granite-4.1-8b
8-bit
Uncategorised · unsloth ↓ 29 · ♥ 0
Params
8.8B
Weights
≈ 9.3 GB
Mac memory
16 GB+

updated 2026-05-04

whisper-large-mlx-8bit

mlx-community/whisper-large-mlx-8bit
8-bit
Uncategorised ↓ 29 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

whisper-medium-asr-fp16

mlx-community/whisper-medium-asr-fp16
fp16
Speech recognition ↓ 29 · ♥ 0
Params
762M
Weights
≈ 1.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-14

whisper-tiny-fp16

from openai/whisper-tiny
fp16
Speech recognition · OpenAI · gpt-oss ↓ 29 · ♥ 0
Params
37M
Weights
≈ 74 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-tiny.en-mlx-fp32

mlx-community/whisper-tiny.en-mlx-fp32
fp32
Uncategorised ↓ 29 · ♥ 0
Params
—
Weights
—
Mac memory
—

updated 2024-03-09

LLaDA2.0-flash-4bit

from inclusionAI/LLaDA2.0-flash
4-bit
Text generation · inclusionAI ↓ 28 · ♥ 3
Params
103B
Weights
≈ 57.9 GB
Mac memory
96 GB+

apache-2.0 · updated 2025-11-25

Soprano-80M-4bit

mlx-community/Soprano-80M-4bit
4-bit
Text to speech ↓ 28 · ♥ 2
Params
94M
Weights
≈ 56 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-04

GUI-Owl-7B-4bit

from mPLUG/GUI-Owl-7B
4-bit
Uncategorised · mPLUG ↓ 28 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-09-22

JoyAI-LLM-Flash-8bit

from jdopensource/JoyAI-LLM-Flash
8-bit
Text generation · jdopensource ↓ 28 · ♥ 1
Params
49B
Weights
≈ 52.0 GB
Mac memory
64 GB+

updated 2026-02-15

LFM2.5-VL-1.6B-6bit

from LiquidAI/LFM2.5-1.2B-Base
6-bit
Vision + text · LiquidAI ↓ 28 · ♥ 1
Params
1.6B
Weights
≈ 1.8 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-06

Llama-3-Smaug-8B-4bit

mlx-community/Llama-3-Smaug-8B-4bit
4-bit
Text generation ↓ 28 · ♥ 1
Params
8.0B
Weights
≈ 4.5 GB
Mac memory
8 GB+

llama2 · updated 2024-04-21

Llama-3.1-SuperNova-Lite-8bit

from meta-llama/Llama-3.1-8B-Instruct
8-bit
Uncategorised · Meta · Llama ↓ 28 · ♥ 1
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

llama3 · updated 2024-09-11

MiniCPM-2B-sft-4bit-llama-format-mlx

mlx-community/MiniCPM-2B-sft-4bit-llama-format-mlx
4-bit
Uncategorised ↓ 28 · ♥ 1
Params
3.0B
Weights
≈ 2.1 GB
Mac memory
8 GB+

updated 2024-04-10

MiniCPM-V-4.6-mxfp4

from openbmb/MiniCPM-V-4.6
MXFP4
Vision + text · openbmb ↓ 28 · ♥ 1
Params
1.3B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-13

Olmo-3-7B-Think-8bit

from allenai/Olmo-3-7B-Think
8-bit
Text generation · Ai2 · OLMo ↓ 28 · ♥ 1
Params
7.3B
Weights
≈ 7.8 GB
Mac memory
16 GB+

apache-2.0 · updated 2025-11-21

QwQ-32b-4bit-DWQ

from Qwen/QwQ-32B
4-bit DWQ
Text generation · Qwen ↓ 28 · ♥ 1
Params
33B
Weights
≈ 18.4 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-05-26

Skywork-SWE-32B-8bit

from Skywork/Skywork-SWE-32B
8-bit
Text generation · Skywork ↓ 28 · ♥ 1
Params
33B
Weights
≈ 34.8 GB
Mac memory
48 GB+

apache-2.0 · updated 2025-06-19

SmallThinker-3B-Preview-4bit

from Tiiny/SmallThinker-3B-Preview
4-bit
Text generation · Tiiny ↓ 28 · ♥ 1
Params
3.1B
Weights
≈ 1.7 GB
Mac memory
8 GB+

updated 2025-01-07

XortronCriminalComputingConfig-4bit

from darkc0de/XortronCriminalComputingConfig
4-bit
Text generation · darkc0de ↓ 28 · ♥ 1
Params
24B
Weights
≈ 13.3 GB
Mac memory
24 GB+

apache-2.0 · updated 2026-02-19

granite-4.0-h-1b-base-8bit

from ibm-granite/granite-4.0-h-1b-base
8-bit
Text generation · IBM · Granite ↓ 28 · ♥ 1
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-10-28

3b-hi-ft-research_release-4bit

from canopylabs/orpheus-3b-0.1-pretrained
4-bit
Text to speech · canopylabs ↓ 28 · ♥ 0
Params
3.3B
Weights
≈ 1.9 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-09

3b-zh-pretrain-research_release-6bit

from meta-llama/Llama-3.2-3B-Instruct
6-bit
Text to speech · Meta · Llama ↓ 28 · ♥ 0
Params
3.3B
Weights
≈ 2.7 GB
Mac memory
8 GB+

llama3.2 · updated 2025-04-10

Cydonia-24B-v3-8bit

from TheDrummer/Cydonia-24B-v3
8-bit
Text generation · TheDrummer ↓ 28 · ♥ 0
Params
24B
Weights
≈ 25.0 GB
Mac memory
32 GB+

other · updated 2025-06-04

DASD-4B-Thinking-bfloat16

from Alibaba-Apsara/DASD-4B-Thinking
Text generation · Alibaba-Apsara ↓ 28 · ♥ 0
Params
4.0B
Weights
≈ 8.0 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-01

Dans-PersonalityEngine-V1.3.0-24b

from PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
6-bit
Text generation · PocketDoc ↓ 28 · ♥ 0
Params
24B
Weights
≈ 19.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-06-23

DeepHermes-3-Llama-3-3B-Preview-8bit

from NousResearch/DeepHermes-3-Llama-3-3B-Preview
8-bit
Text generation · NousResearch ↓ 28 · ♥ 0
Params
3.2B
Weights
≈ 3.4 GB
Mac memory
8 GB+

llama3 · updated 2025-03-14

EXAONE-3.5-32B-Instruct-3bit

mlx-community/EXAONE-3.5-32B-Instruct-3bit
3-bit
Uncategorised ↓ 28 · ♥ 0
Params
4.0B
Weights
≈ 3.3 GB
Mac memory
8 GB+

updated 2024-12-10

EXAONE-3.5-32B-Instruct-6bit

mlx-community/EXAONE-3.5-32B-Instruct-6bit
6-bit
Uncategorised ↓ 28 · ♥ 0
Params
7.0B
Weights
≈ 6.9 GB
Mac memory
16 GB+

updated 2024-12-10

Falcon-H1-Tiny-R-0.6B-bf16

from tiiuae/Falcon-H1-Tiny-R-0.6B
bf16
Text generation · TII · Falcon ↓ 28 · ♥ 0
Params
622M
Weights
≈ 1.2 GB
Mac memory
8 GB+

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

Falcon-H1-Tiny-R-90M-6bit

from tiiuae/Falcon-H1-Tiny-R-90M
6-bit
Text generation · TII · Falcon ↓ 28 · ♥ 0
Params
91M
Weights
≈ 74 MB
Mac memory
8 GB+

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

Falcon3-10B-Instruct-6bit

from tiiuae/Falcon3-10B-Instruct
6-bit
Text generation · TII · Falcon ↓ 28 · ♥ 0
Params
10B
Weights
≈ 8.4 GB
Mac memory
16 GB+

falcon-llm-license · updated 2024-12-18

Falcon3-3B-Instruct-bf16

from tiiuae/Falcon3-3B-Instruct
bf16
Text generation · TII · Falcon ↓ 28 · ♥ 0
Params
3.2B
Weights
≈ 6.5 GB
Mac memory
16 GB+

falcon-llm-license · updated 2024-12-17

Gemma-SEA-LION-v4-27B-IT-bf16

from aisingapore/Gemma-SEA-LION-v4-27B-IT
bf16
Text generation · aisingapore ↓ 28 · ♥ 0
Params
27B
Weights
≈ 54.0 GB
Mac memory
64 GB+

gemma · updated 2026-02-21

Huihui-LFM2.5-1.2B-Instruct-abliterated-8bit

from huihui-ai/Huihui-LFM2.5-1.2B-Instruct-abliterated
8-bit
Text generation · huihui-ai ↓ 28 · ♥ 0
Params
1.2B
Weights
≈ 1.2 GB
Mac memory
8 GB+

lfm1.0 · updated 2026-01-26

Hunyuan-A13B-Instruct-4bit-DWQ

from tencent/Hunyuan-A13B-Instruct
4-bit DWQ
Text generation · tencent ↓ 28 · ♥ 0
Params
80B
Weights
≈ 45.2 GB
Mac memory
64 GB+

tencent-hunyuan-a13b · updated 2025-07-13

Impish_LLAMA_3B-6bit

from SicariusSicariiStuff/Impish_LLAMA_3B
6-bit
Uncategorised · SicariusSicariiStuff ↓ 28 · ♥ 0
Params
3.2B
Weights
≈ 2.6 GB
Mac memory
8 GB+

llama3.2 · updated 2025-02-26

JOSIE-IT1-Qwen3-0.6B-4bit

from Goekdeniz-Guelmez/JOSIE-IT1-Qwen3-0.6B
4-bit
Text generation · Goekdeniz-Guelmez ↓ 28 · ♥ 0
Params
596M
Weights
≈ 335 MB
Mac memory
8 GB+

updated 2026-01-12

Jan-v1-edge-8bit

from janhq/Jan-v1-edge
8-bit
Text generation · janhq ↓ 28 · ♥ 0
Params
1.7B
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-09-04

Jan-v2-VL-low-4bit-mlx

from janhq/Jan-v2-VL-low
4-bit
Uncategorised · janhq ↓ 28 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2025-11-15

Josiefied-Qwen3-0.6B-abliterated-v2-bfloat16

from Goekdeniz-Guelmez/Josiefied-Qwen3-0.6B-abliterated-v2
Text generation · Goekdeniz-Guelmez ↓ 28 · ♥ 0
Params
596M
Weights
≈ 1.2 GB
Mac memory
8 GB+

updated 2026-01-11

LLaDA-8B-Instruct-mlx-8bit

from GSAI-ML/LLaDA-8B-Instruct
8-bit
Text generation · GSAI-ML ↓ 28 · ♥ 0
Params
8.0B
Weights
≈ 8.5 GB
Mac memory
16 GB+

mit · updated 2025-03-12

Laguna-XS.2-5bit

from poolside/Laguna-XS.2
5-bit
Text generation · poolside ↓ 28 · ♥ 0
Params
33B
Weights
≈ 23.0 GB
Mac memory
32 GB+

apache-2.0 · updated 2026-04-28

Ling-mini-2.0-6bit

from inclusionAI/Ling-mini-2.0
6-bit
Text generation · inclusionAI ↓ 28 · ♥ 0
Params
16B
Weights
≈ 13.2 GB
Mac memory
24 GB+

mit · updated 2025-09-15

Lingshu-7B-4bit

mlx-community/Lingshu-7B-4bit
4-bit
Vision + text ↓ 28 · ♥ 0
Params
8.3B
Weights
≈ 4.9 GB
Mac memory
8 GB+

mit · updated 2025-06-12

MiniCPM-V-4.6-nvfp4

from openbmb/MiniCPM-V-4.6
4-bit
Vision + text · openbmb ↓ 28 · ♥ 0
Params
1.3B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-13

Nemotron-Cascade-2-30B-A3B-mxfp8

from nvidia/Nemotron-Cascade-2-30B-A3B
MXFP8
Text generation · NVIDIA ↓ 28 · ♥ 0
Params
32B
Weights
≈ 33.6 GB
Mac memory
48 GB+

nvidia-open-model-license · updated 2026-04-30

Nex-N2-mini-8bit

from nex-agi/Nex-N2-mini
8-bit
Text generation · nex-agi ↓ 28 · ♥ 0
Params
35B
Weights
≈ 37.7 GB
Mac memory
48 GB+

apache-2.0 · updated 2026-06-08

Nova-Tempus-70B-v0.1-MLX-8Bit

from sophosympatheia/Nova-Tempus-70B-v0.1
8-bit
Text generation · sophosympatheia ↓ 28 · ♥ 0
Params
71B
Weights
≈ 75.0 GB
Mac memory
96 GB+

llama3.3 · updated 2025-01-26

OlympicCoder-7B-mlx-fp16

from open-r1/OlympicCoder-7B
fp16
Text generation · open-r1 ↓ 28 · ♥ 0
Params
7.6B
Weights
≈ 15.2 GB
Mac memory
24 GB+

apache-2.0 · updated 2025-03-12

Pleias-RAG-350M-4-bit

from PleIAs/Pleias-RAG-350M
4-bit
Text generation · PleIAs ↓ 28 · ♥ 0
Params
353M
Weights
≈ 199 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-04-24

Polaris-4B-Preview-5bit

from POLARIS-Project/Polaris-4B-Preview
5-bit
Text generation · POLARIS-Project ↓ 28 · ♥ 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 ↓ 28 · ♥ 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 ↓ 28 · ♥ 0
Params
7.6B
Weights
≈ 8.1 GB
Mac memory
16 GB+

apache-2.0 · updated 2024-08-09

Qwen3-30B-A3B-Instruct-2507-6bit-DWQ-lr3e-7

from Qwen/Qwen3-30B-A3B-Instruct-2507
6-bit DWQ
Text generation · Qwen ↓ 28 · ♥ 0
Params
31B
Weights
≈ 24.8 GB
Mac memory
32 GB+

apache-2.0 · updated 2025-07-31

Qwen3-TTS-12Hz-0.6B-CustomVoice-5bit

mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-5bit
5-bit
Text to speech ↓ 28 · ♥ 0
Params
906M
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-25