Apple MLX models

gemma-4-e2b-it-OptiQ-4bit

from google/gemma-4-E2B-it

4-bit

Text generation · Google · Gemma ↓ 533 · ♥ 4

Params

4.6B

Weights

≈ 2.6 GB

Mac memory

8 GB+

gemma · updated 2026-10-18

unsloth-gemma-4-E4B-it-qat-oQ4

from unsloth/gemma-4-E4B-it-qat-q4_0-unquantized

4-bit

Any to any · unsloth ↓ 532 · ♥ 5

Params

7.9B

Weights

≈ 5.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-07-06

LFM2-350M-8bit

from LiquidAI/LFM2-350M

8-bit

Text generation · LiquidAI ↓ 529 · ♥ 4

Params

354M

Weights

≈ 377 MB

Mac memory

8 GB+

lfm1.0 · updated 2025-07-11

Unlimited-OCR-8bit

from baidu/Unlimited-OCR

8-bit

Vision + text · baidu ↓ 529 · ♥ 3

Params

3.3B

Weights

≈ 3.9 GB

Mac memory

8 GB+

mit · updated 2026-07-31

Fun-CosyVoice3-0.5B-2512-4bit

from FunAudioLLM/Fun-CosyVoice3-0.5B-2512

4-bit

Text to speech · FunAudioLLM ↓ 528 · ♥ 3

Params

866M

Weights

≈ 1.2 GB

Mac memory

8 GB+

updated 2025-12-17

Agents-A1-4bit

from InternScience/Agents-A1

4-bit

Vision + text · InternScience ↓ 527 · ♥ 6

Params

35B

Weights

≈ 20.4 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-07-01

GLM-5.2-4bit

from zai-org/GLM-5.2

4-bit

Text generation · zai-org ↓ 527 · ♥ 6

Params

743B

Weights

≈ 418 GB

Mac memory

512 GB+

mit · updated 2026-07-12

Qwen3.5-27B-8bit

mlx-community/Qwen3.5-27B-8bit

8-bit

Vision + text ↓ 525 · ♥ 7

Params

27B

Weights

≈ 29.5 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-02-24

Qwen3-Coder-Next-5bit

from Qwen/Qwen3-Coder-Next

5-bit

Text generation · Qwen ↓ 523 · ♥ 4

Params

80B

Weights

≈ 54.8 GB

Mac memory

64 GB+

apache-2.0 · updated 2026-02-03

LFM2-1.2B-4bit

from LiquidAI/LFM2-1.2B

4-bit

Text generation · LiquidAI ↓ 520 · ♥ 2

Params

1.2B

Weights

≈ 659 MB

Mac memory

8 GB+

lfm1.0 · updated 2025-07-11

Qwen3.5-0.8B-MLX-8bit

from Qwen/Qwen3.5-0.8B

8-bit

Uncategorised · Qwen ↓ 519 · ♥ 5

Params

853M

Weights

≈ 1.0 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-02

gemma-4-e4b-it-6bit

from google/gemma-4-E4B-it

6-bit

Vision + text · Google · Gemma ↓ 519 · ♥ 3

Params

7.9B

Weights

≈ 7.0 GB

Mac memory

16 GB+

gemma · updated 2026-07-06

Ming-3.0-tts-tiny-8bit

from inclusionAI/Ming-3.0-tts-tiny

8-bit

Text to speech · inclusionAI ↓ 517 · ♥ 1

Params

9.0B

Weights

≈ 10.6 GB

Mac memory

16 GB+

mit · updated 2026-10-19

LFM2.5-VL-3B-OptiQ-4bit

from LiquidAI/LFM2.5-VL-3B

4-bit

Vision + text · LiquidAI ↓ 513 · ♥ 2

Params

2.7B

Weights

≈ 1.5 GB

Mac memory

8 GB+

lfm1.0 · updated 2026-10-18

CosyVoice2-0.5B-8bit

from FunAudioLLM/CosyVoice2-0.5B

8-bit

Text to speech · FunAudioLLM ↓ 513 · ♥ 1

Params

646M

Weights

≈ 957 MB

Mac memory

8 GB+

updated 2025-12-11

NVIDIA-Nemotron-3-Super-120B-A12B-4bit

from nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

4-bit

Text generation · NVIDIA ↓ 513 · ♥ 1

Params

121B

Weights

≈ 68.0 GB

Mac memory

96 GB+

nvidia-nemotron-open-model-license · updated 2026-03-30

gemma-4-12B-it-qat-mxfp4

mlx-community/gemma-4-12B-it-qat-mxfp4

MXFP4

Vision + text ↓ 511 · ♥ 1

Params

12B

Weights

≈ 6.7 GB

Mac memory

16 GB+

updated 2026-06-05

gemma-4-26b-a4b-it-5bit

from google/gemma-4-26B-A4B-it

5-bit

Vision + text · Google · Gemma ↓ 509 · ♥ 3

Params

26B

Weights

≈ 18.5 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-07-05

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-4bit

from nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

4-bit

Vision + text · NVIDIA ↓ 509 · ♥ 2

Params

33B

Weights

≈ 19.6 GB

Mac memory

24 GB+

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

embeddinggemma-300m-bf16

mlx-community/embeddinggemma-300m-bf16

bf16

Sentence similarity ↓ 508 · ♥ 5

Params

308M

Weights

≈ 615 MB

Mac memory

8 GB+

gemma · updated 2025-09-04

MiniCPM-V-4.7-35B-A3B-bf16

from openbmb/MiniCPM-V-4.7-35B-A3B

bf16

Vision + text · openbmb ↓ 507 · ♥ 2

Params

35B

Weights

≈ 70.4 GB

Mac memory

96 GB+

apache-2.0 · updated 2026-10-13

Olmo-3.1-32B-Think-4bit

from allenai/Olmo-3.1-32B-Think

4-bit

Text generation · Ai2 · OLMo ↓ 504 · ♥ 0

Params

32B

Weights

≈ 18.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-12-24

granite-4.0-h-1b-6bit

from ibm-granite/granite-4.0-h-1b

6-bit

Text generation · IBM · Granite ↓ 502 · ♥ 0

Params

1.5B

Weights

≈ 1.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-28

GLM-4.5-Air-3bit

from zai-org/GLM-4.5-Air

3-bit

Text generation · zai-org ↓ 501 · ♥ 33

Params

107B

Weights

≈ 46.8 GB

Mac memory

64 GB+

mit · updated 2025-07-28

gemma-4-12B-it-mxfp4

mlx-community/gemma-4-12B-it-mxfp4

MXFP4

Vision + text ↓ 501 · ♥ 2

Params

12B

Weights

≈ 6.7 GB

Mac memory

16 GB+

updated 2026-06-08

MiniCPM-o-4_5-4bit

mlx-community/MiniCPM-o-4_5-4bit

4-bit

Any to any ↓ 499 · ♥ 1

Params

9.0B

Weights

≈ 6.1 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-05

bge-small-en-v1.5-8bit

mlx-community/bge-small-en-v1.5-8bit

8-bit

Embeddings ↓ 498 · ♥ 1

Params

33M

Weights

≈ 36 MB

Mac memory

8 GB+

mit · updated 2025-04-02

Olmo-3.1-32B-Instruct-4bit

from allenai/Olmo-3.1-32B-Instruct

4-bit

Text generation · Ai2 · OLMo ↓ 494 · ♥ 0

Params

32B

Weights

≈ 18.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-12-23

MiniMax-Music3-4bit

from MiniMaxAI/MiniMax-Music3

4-bit

Text to audio · MiniMaxAI ↓ 492 · ♥ 8

Params

12B

Weights

≈ 9.2 GB

Mac memory

16 GB+

minimax-music3-community-license · updated 2026-08-16

Gemma4-E2B-IT-Text-int4

from google/gemma-4-E2B-it

Text generation · Google · Gemma ↓ 491 · ♥ 2

Params

738M

Weights

≈ 2.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-05-19

Ling-3.1-flash-1019-oQ2.5e-mtp

from inclusionAI/Ling-3.1-flash-1019

2-bit

Text generation · inclusionAI ↓ 491 · ♥ 0

Params

572B

Weights

≈ 179 GB

Mac memory

256 GB+

mit · updated 2026-10-28

Dolphin3.0-R1-Mistral-24B-4bit

from dphn/Dolphin3.0-R1-Mistral-24B

4-bit

Text generation · dphn ↓ 487 · ♥ 2

Params

24B

Weights

≈ 13.3 GB

Mac memory

24 GB+

updated 2025-02-16

NemotronLabs-VoiceChat-11B-8bit

from nvidia/NVIDIA-NemotronLabs-VoiceChat-11B

8-bit

Uncategorised · NVIDIA ↓ 485 · ♥ 13

Params

11B

Weights

≈ 13.3 GB

Mac memory

24 GB+

openmdw-1.1 · updated 2026-08-08

Xing4.0-29B-A4B-OptiQ-4bit

from XingChen-AGI/Xing4.0-29B-A4B

4-bit

Text generation · XingChen-AGI ↓ 484 · ♥ 7

Params

30B

Weights

≈ 16.6 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-09-23

gemma-4-12B-it-bf16

mlx-community/gemma-4-12B-it-bf16

bf16

Vision + text ↓ 481 · ♥ 5

Params

12B

Weights

≈ 23.9 GB

Mac memory

32 GB+

updated 2026-06-03

Qwen3.5-2B-8bit

from Qwen/Qwen3.5-2B-Base

8-bit

Vision + text · Qwen ↓ 480 · ♥ 1

Params

2.2B

Weights

≈ 2.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-02

MOSS-TTS-Local-Transformer-v1.5-8bit

from OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5

8-bit

Text to speech · OpenMOSS-Team ↓ 480 · ♥ 0

Params

4.6B

Weights

≈ 4.9 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-09-02

NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

from nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4

4-bit

Text generation · NVIDIA ↓ 478 · ♥ 9

Params

32B

Weights

≈ 19.3 GB

Mac memory

24 GB+

nvidia-open-model-license · updated 2026-01-29

Qwen2.5-Omni-3B-Thinker-4bit

from Qwen/Qwen2.5-Omni-3B

4-bit

Uncategorised · Qwen ↓ 477 · ♥ 1

Params

—

Weights

—

Mac memory

—

qwen-research · updated 2026-11-02

Phi-4-mini-instruct-mlx-4Bit

from microsoft/Phi-4-mini-instruct

4-bit

Text generation · Microsoft · Phi ↓ 475 · ♥ 2

Params

3.8B

Weights

≈ 2.2 GB

Mac memory

8 GB+

mit · updated 2026-07-27

Ling-3.1-flash-1019-oQ3e-mtp

from inclusionAI/Ling-3.1-flash-1019

3-bit

Text generation · inclusionAI ↓ 475 · ♥ 0

Params

572B

Weights

≈ 250 GB

Mac memory

512 GB+

mit · updated 2026-10-28

NVIDIA-Nemotron-Nano-9B-v2-4bits

from nvidia/NVIDIA-Nemotron-Nano-9B-v2

4-bit

Text generation · NVIDIA ↓ 474 · ♥ 4

Params

1.4B

Weights

≈ 1.2 GB

Mac memory

8 GB+

nvidia-open-model-license · updated 2025-08-28

DeepSeek-OCR-2-bf16

mlx-community/DeepSeek-OCR-2-bf16

bf16

Vision + text ↓ 470 · ♥ 9

Params

3.4B

Weights

≈ 6.8 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-01-28

PaddleOCR-VL-1.6-5bit

from PaddlePaddle/PaddleOCR-VL-1.6

5-bit

Vision + text · PaddlePaddle ↓ 470 · ♥ 0

Params

906M

Weights

≈ 800 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-08-12

flux-3-image-klein-pup-4bit

from black-forest-labs/flux-3-image-klein-pup

4-bit

Vision + text · black-forest-labs ↓ 465 · ♥ 0

Params

9.4B

Weights

≈ 6.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-10-18

LFM2.5-8B-A1B-OptiQ-4bit

from LiquidAI/LFM2.5-8B-A1B

4-bit

Text generation · LiquidAI ↓ 461 · ♥ 2

Params

8.5B

Weights

≈ 4.8 GB

Mac memory

8 GB+

lfm1.0 · updated 2026-10-14

Olmo-3-7B-Instruct-mxfp4-QAT

from allenai/Olmo-3-7B-Instruct

MXFP4

Text generation · Ai2 · OLMo ↓ 458 · ♥ 4

Params

7.3B

Weights

≈ 4.1 GB

Mac memory

8 GB+

updated 2026-04-23

Hemmingway-1-OptiQ-4bit

from HemmingwayAI/Hemmingway-1

4-bit

Text generation · HemmingwayAI ↓ 458 · ♥ 3

Params

27B

Weights

≈ 15.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-10-30

Voxtral-Mini-4B-Realtime-2602-fp16

from mistralai/Voxtral-Mini-4B-Realtime-2602

fp16

Speech recognition · Mistral ↓ 456 · ♥ 3

Params

4.4B

Weights

≈ 8.9 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-02-09

gemma-4-E2B-it-assistant-bf16

from google/gemma-4-E2B-it-assistant

bf16

Text generation · Google · Gemma ↓ 454 · ♥ 7

Params

78M

Weights

≈ 158 MB

Mac memory

8 GB+

gemma · updated 2026-05-05

gemma-4-e4b-4bit

from google/gemma-4-e4b

4-bit

Any to any · Google · Gemma ↓ 454 · ♥ 7

Params

8.0B

Weights

≈ 5.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-03

GLM-5.1

mlx-community/GLM-5.1

Text generation ↓ 454 · ♥ 5

Params

744B

Weights

≈ 1488 GB

Mac memory

> 512 GB

updated 2026-04-07

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

from google/gemma-4-12B-it-qat-q4_0-unquantized-assistant

4-bit

Text generation · Google · Gemma ↓ 454 · ♥ 3

Params

423M

Weights

≈ 238 MB

Mac memory

8 GB+

gemma · updated 2026-06-05

JevK5-chat-mlx-16bit

from alibiserikbay/JevK5

16-bit

Text generation · alibiserikbay ↓ 454 · ♥ 1

Params

4.2B

Weights

≈ 8.4 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-10-14

Mistral-7B-Instruct-v0.2

mlx-community/Mistral-7B-Instruct-v0.2

Text generation ↓ 452 · ♥ 20

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2023-12-23

mel-roformer-zfturbo-vocals-v1-mlx

mlx-community/mel-roformer-zfturbo-vocals-v1-mlx

Audio to audio ↓ 452 · ♥ 2

Params

34M

Weights

≈ 67 MB

Mac memory

8 GB+

mit · updated 2026-05-01

orpheus-3b-0.1-ft-8bit

from canopylabs/orpheus-3b-0.1-ft

8-bit

Text to speech · canopylabs ↓ 452 · ♥ 2

Params

3.3B

Weights

≈ 3.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-03-21

LFM2-2.6B-4bit

from LiquidAI/LFM2-2.6B

4-bit

Text generation · LiquidAI ↓ 450 · ♥ 1

Params

2.6B

Weights

≈ 1.4 GB

Mac memory

8 GB+

lfm1.0 · updated 2025-09-23

Qwen3.5-27B-OptiQ-4bit

from Qwen/Qwen3.5-27B

4-bit

Text generation · Qwen ↓ 449 · ♥ 3

Params

27B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-10-30

Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-Heretic-OptiQ-4bit

from DavidAU/Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-Heretic

4-bit

Text generation · DavidAU ↓ 447 · ♥ 2

Params

27B

Weights

≈ 15.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-09-16