Apple MLX models

gemma-3-text-12b-pt-4bit

from mlx-community/gemma-3-12b-pt-bf16

4-bit

Text generation ↓ 62 · ♥ 0

Params

13B

Weights

≈ 7.2 GB

Mac memory

16 GB+

gemma · updated 2025-03-18

DiffuCoder-7B-cpGRPO-4bit

from apple/DiffuCoder-7B-cpGRPO

4-bit

Text generation · apple ↓ 61 · ♥ 4

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

unknown · updated 2025-07-04

Agents-A1-bf16

from InternScience/Agents-A1

bf16

Vision + text · InternScience ↓ 61 · ♥ 3

Params

35B

Weights

≈ 70.2 GB

Mac memory

96 GB+

apache-2.0 · updated 2026-07-01

DeepHermes-3-Mistral-24B-Preview-8bit

from NousResearch/DeepHermes-3-Mistral-24B-Preview

8-bit

Text generation · NousResearch ↓ 61 · ♥ 3

Params

24B

Weights

≈ 25.0 GB

Mac memory

32 GB+

apache-2.0 · updated 2025-03-14

aya-vision-8b-8bit

mlx-community/aya-vision-8b-8bit

8-bit

Vision + text ↓ 61 · ♥ 3

Params

8.6B

Weights

≈ 9.6 GB

Mac memory

16 GB+

cc-by-nc-4.0 · updated 2025-03-05

c4ai-command-r-plus-8bit

mlx-community/c4ai-command-r-plus-8bit

8-bit

Text generation ↓ 61 · ♥ 3

Params

104B

Weights

≈ 113 GB

Mac memory

192 GB+

cc-by-nc-4.0 · updated 2024-04-12

Macaw-OptiQ-4bit

from badtheorylabs/Macaw

4-bit

Text generation · badtheorylabs ↓ 61 · ♥ 2

Params

2.7B

Weights

≈ 1.5 GB

Mac memory

8 GB+

lfm-open-license-v1.0 · updated 2026-09-15

Phi-3.5-vision-instruct-bf16

mlx-community/Phi-3.5-vision-instruct-bf16

bf16

Text generation ↓ 61 · ♥ 2

Params

4.1B

Weights

≈ 8.3 GB

Mac memory

16 GB+

mit · updated 2025-04-19

Qwen3-235B-A22B-Instruct-2507-4bit-DWQ

from mlx-community/Qwen3-235B-A22B-Instruct-2507-8bit

4-bit DWQ

Text generation ↓ 61 · ♥ 2

Params

235B

Weights

≈ 132 GB

Mac memory

192 GB+

apache-2.0 · updated 2025-07-25

Qwen3-VL-235B-A22B-Instruct-3bit

mlx-community/Qwen3-VL-235B-A22B-Instruct-3bit

3-bit

Uncategorised ↓ 61 · ♥ 2

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-10-13

Qwen3.6-35B-A3B-4.4bit-msq

mlx-community/Qwen3.6-35B-A3B-4.4bit-msq

4-bit

Vision + text ↓ 61 · ♥ 2

Params

35B

Weights

≈ 5.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-16

phi-2-hf-4bit-mlx

mlx-community/phi-2-hf-4bit-mlx

4-bit

Text generation ↓ 61 · ♥ 2

Params

—

Weights

—

Mac memory

—

mit · updated 2024-01-14

AIDC-AI_Marco-o1_MLX-4bit

from ATH-MaaS/Marco-o1

4-bit

Text generation · ATH-MaaS ↓ 61 · ♥ 1

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-11-27

DeepSeek-V3.1-mlx-DQ5_K_M

from deepseek-ai/DeepSeek-V3.1

4-bit

Text generation · DeepSeek ↓ 61 · ♥ 1

Params

671B

Weights

≈ 378 GB

Mac memory

512 GB+

mit · updated 2025-09-10

GLM-4.6V-Flash-6bit

mlx-community/GLM-4.6V-Flash-6bit

6-bit

Vision + text ↓ 61 · ♥ 1

Params

—

Weights

—

Mac memory

—

mit · updated 2025-12-08

Llama-4-Maverick-17B-128E-Instruct-6bit

from meta-llama/Llama-4-Maverick-17B-128E

6-bit

Vision + text · Meta · Llama ↓ 61 · ♥ 1

Params

—

Weights

—

Mac memory

—

llama4 · updated 2025-04-07

LongCat-Flash-Lite-Sparse-6bit

from meituan-longcat/LongCat-Flash-Lite-Sparse

6-bit

Text generation · meituan-longcat ↓ 61 · ♥ 1

Params

69B

Weights

≈ 55.7 GB

Mac memory

96 GB+

mit · updated 2026-08-31

Ministral-3-3B-Instruct-2512-5bit

from mistralai/Ministral-3-3B-Base-2512

5-bit

Uncategorised · Mistral ↓ 61 · ♥ 1

Params

3.8B

Weights

≈ 3.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-12-03

Phi-3.5-mini-instruct-bf16

mlx-community/Phi-3.5-mini-instruct-bf16

bf16

Text generation ↓ 61 · ♥ 1

Params

3.8B

Weights

≈ 7.6 GB

Mac memory

16 GB+

mit · updated 2024-08-20

gemma-4-26B-A4B-it-qat-assistant-mxfp8

from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant

MXFP8

Text generation · Google · Gemma ↓ 61 · ♥ 1

Params

420M

Weights

≈ 446 MB

Mac memory

8 GB+

gemma · updated 2026-06-05

gemma-4-31B-it-qat-bf16

mlx-community/gemma-4-31B-it-qat-bf16

bf16

Vision + text ↓ 61 · ♥ 1

Params

31B

Weights

≈ 62.5 GB

Mac memory

96 GB+

updated 2026-06-05

granite-4.0-3b-vision-5bit

from ibm-granite/granite-4.0-3b-vision

5-bit

Vision + text · IBM · Granite ↓ 61 · ♥ 1

Params

4.3B

Weights

≈ 3.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-01

perplexity-ai-r1-1776-bf16

from perplexity-ai/r1-1776

bf16

Uncategorised · perplexity-ai ↓ 61 · ♥ 1

Params

671B

Weights

≈ 1342 GB

Mac memory

> 512 GB

mit · updated 2025-02-25

una-cybertron-7b-v2-bf16-4bit-mlx

mlx-community/una-cybertron-7b-v2-bf16-4bit-mlx

4-bit

Text generation ↓ 61 · ♥ 1

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-14

DeepSeek-R1-Distill-Qwen-1.5B-MLX-Q8

from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

8-bit

Text generation · DeepSeek ↓ 61 · ♥ 0

Params

1.8B

Weights

≈ 1.9 GB

Mac memory

8 GB+

mit · updated 2025-03-17

DeepSeek-R1-Distill-Qwen-7B-3bit

from deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

3-bit

Uncategorised · DeepSeek ↓ 61 · ♥ 0

Params

7.6B

Weights

≈ 3.3 GB

Mac memory

8 GB+

updated 2025-02-26

INTELLECT-1-Instruct-3bit

from PrimeIntellect/INTELLECT-1-Instruct

3-bit

Text generation · PrimeIntellect ↓ 61 · ♥ 0

Params

10B

Weights

≈ 4.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-11-30

Josiefied-Hermes-3-Llama-3.2-3B-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Hermes-3-Llama-3.2-3B-v1

4-bit

Text generation · Goekdeniz-Guelmez ↓ 61 · ♥ 0

Params

3.2B

Weights

≈ 1.8 GB

Mac memory

8 GB+

updated 2025-10-28

LFM2.5-350M-8bit

from LiquidAI/LFM2.5-350M

8-bit

Text generation · LiquidAI ↓ 61 · ♥ 0

Params

354M

Weights

≈ 377 MB

Mac memory

8 GB+

lfm1.0 · updated 2026-08-13

Ministral-3-8B-Instruct-2512-bf16

from mistralai/Ministral-3-8B-Base-2512

bf16

Uncategorised · Mistral ↓ 61 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-12-03

NuExtract3-bf16

from numind/NuExtract3

bf16

Vision + text · numind ↓ 61 · ♥ 0

Params

4.5B

Weights

≈ 9.1 GB

Mac memory

16 GB+

updated 2026-05-20

OLMo-2-1124-13B-Instruct-4bit

from allenai/OLMo-2-1124-13B-Instruct

4-bit

Text generation · Ai2 · OLMo ↓ 61 · ♥ 0

Params

14B

Weights

≈ 7.7 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-11-27

Qwen2.5-1.5B-Instruct-abliterated-6bit

from huihui-ai/Qwen2.5-1.5B-Instruct-abliterated

6-bit

Text generation · huihui-ai ↓ 61 · ♥ 0

Params

1.5B

Weights

≈ 1.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-02-26

Qwen2.5-1.5B-bf16

mlx-community/Qwen2.5-1.5B-bf16

bf16

Text generation ↓ 61 · ♥ 0

Params

1.5B

Weights

≈ 3.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-09-18

SongGeneration-v2-large

from tencent/SongGeneration

Text to audio · tencent ↓ 61 · ♥ 0

Params

5.1B

Weights

≈ 10.2 GB

Mac memory

16 GB+

other · updated 2026-05-31

codegemma-2b-4bit

mlx-community/codegemma-2b-4bit

4-bit

Text generation ↓ 61 · ♥ 0

Params

2.5B

Weights

≈ 2.2 GB

Mac memory

8 GB+

gemma · updated 2024-04-09

gemma-3-4b-it-abliterated-8bit-text

from mlabonne/gemma-3-4b-it-abliterated

8-bit

Text generation · mlabonne ↓ 61 · ♥ 0

Params

4.6B

Weights

≈ 4.8 GB

Mac memory

8 GB+

gemma · updated 2025-03-22

gemma-4-26B-A4B-it-qat-assistant-nvfp4

from google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant

4-bit

Text generation · Google · Gemma ↓ 61 · ♥ 0

Params

420M

Weights

≈ 236 MB

Mac memory

8 GB+

gemma · updated 2026-06-05

gemma-4-E4B-it-qat-assistant-8bit

from google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant

8-bit

Text generation · Google · Gemma ↓ 61 · ♥ 0

Params

79M

Weights

≈ 84 MB

Mac memory

8 GB+

gemma · updated 2026-06-05

whisper-tiny-4bit

from openai/whisper-tiny

4-bit

Speech recognition · OpenAI · gpt-oss ↓ 61 · ♥ 0

Params

37M

Weights

≈ 22 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-12-15

dbrx-instruct-4bit

mlx-community/dbrx-instruct-4bit

4-bit

Uncategorised ↓ 60 · ♥ 49

Params

132B

Weights

≈ 74.9 GB

Mac memory

96 GB+

databricks-open-model-license · updated 2024-04-09

IQuest-Coder-V1-40B-Instruct-8bit

from IQuestLab/IQuest-Coder-V1-40B-Instruct

8-bit

Text generation · IQuestLab ↓ 60 · ♥ 6

Params

40B

Weights

≈ 42.3 GB

Mac memory

64 GB+

iquestcoder · updated 2026-01-01

deepcogito-cogito-v1-preview-qwen-32B-4bit

from deepcogito/cogito-v1-preview-qwen-32B

4-bit

Text generation · deepcogito ↓ 60 · ♥ 5

Params

33B

Weights

≈ 18.4 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-04-09

LFM2-8B-A1B-8bit

from LiquidAI/LFM2-8B-A1B

8-bit

Text generation · LiquidAI ↓ 60 · ♥ 3

Params

8.3B

Weights

≈ 8.9 GB

Mac memory

16 GB+

lfm1.0 · updated 2025-10-08

Mistral-Nemo-Base-2407-8bit

mlx-community/Mistral-Nemo-Base-2407-8bit

8-bit

Uncategorised ↓ 60 · ♥ 3

Params

12B

Weights

≈ 13.0 GB

Mac memory

24 GB+

apache-2.0 · updated 2024-07-18

ERNIE-4.5-300B-A47B-PT-4bit

from baidu/ERNIE-4.5-300B-A47B-PT

4-bit

Text generation · baidu ↓ 60 · ♥ 2

Params

299B

Weights

≈ 168 GB

Mac memory

192 GB+

apache-2.0 · updated 2025-07-04

Josiefied-Qwen3-8B-abliterated-v1-bf16

from Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1

bf16

Text generation · Goekdeniz-Guelmez ↓ 60 · ♥ 2

Params

8.2B

Weights

≈ 16.4 GB

Mac memory

24 GB+

updated 2025-05-01

Mistral-7B-v0.3-4bit

mlx-community/Mistral-7B-v0.3-4bit

4-bit

Uncategorised ↓ 60 · ♥ 2

Params

7.2B

Weights

≈ 4.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-05-22

Raon-Speech-9B

mlx-community/Raon-Speech-9B

Any to any ↓ 60 · ♥ 2

Params

9.0B

Weights

≈ 18.1 GB

Mac memory

24 GB+

cc-by-nc-4.0 · updated 2026-04-02

Apertus-SEA-LION-v4-8B-IT

from aisingapore/Apertus-SEA-LION-v4-8B-IT

Text generation · aisingapore ↓ 60 · ♥ 1

Params

8.1B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-02-19

Ming-omni-tts-16.8B-A3B-bf16

mlx-community/Ming-omni-tts-16.8B-A3B-bf16

bf16

Text to speech ↓ 60 · ♥ 1

Params

18B

Weights

≈ 35.8 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-03-06

Mistral-7B-Instruct-v0.2-8-bit-mlx

mlx-community/Mistral-7B-Instruct-v0.2-8-bit-mlx

8-bit

Text generation ↓ 60 · ♥ 1

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-04

Octen-Embedding-4B-MLX-4bit

from Octen/Octen-Embedding-4B

4-bit

Embeddings · Octen ↓ 60 · ♥ 1

Params

4.0B

Weights

≈ 2.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-08-24

QwQ-32B-Preview-2bit

from Qwen/QwQ-32B-Preview

2-bit

Text generation · Qwen ↓ 60 · ♥ 1

Params

33B

Weights

≈ 10.2 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-12-23

shisa-v2-llama3.3-70b-4bit

from shisa-ai/shisa-v2-llama3.3-70b

4-bit

Text generation · shisa-ai ↓ 60 · ♥ 1

Params

71B

Weights

≈ 39.7 GB

Mac memory

48 GB+

llama3.3 · updated 2025-04-15

FLUX.2-Klein-4B-5bit

from black-forest-labs/FLUX.2-klein-4B

5-bit

Image to image · black-forest-labs ↓ 60 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2026-05-29

GLM-4.1V-9B-Thinking-5bit

from zai-org/GLM-4-9B-0414

5-bit

Vision + text · zai-org ↓ 60 · ♥ 0

Params

—

Weights

—

Mac memory

—

mit · updated 2025-11-10

GOT-OCR2_0-bf16

from stepfun-ai/GOT-OCR2_0

bf16

Vision + text · stepfun-ai ↓ 60 · ♥ 0

Params

561M

Weights

≈ 1.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-08-14

Mistral-7B-v0.1-sql

mlx-community/Mistral-7B-v0.1-sql

Text generation ↓ 60 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-14

magnum-v2-72b-4bit

from anthracite-org/magnum-v2-72b

4-bit

Text generation · anthracite-org ↓ 60 · ♥ 0

Params

73B

Weights

≈ 40.9 GB

Mac memory

48 GB+

tongyi-qianwen · updated 2024-12-17