Apple MLX models

Qwen3-30B-A3B-Instruct-2507-6bit

from Qwen/Qwen3-30B-A3B-Instruct-2507

6-bit

Text generation · Qwen ↓ 69 · ♥ 0

Params

31B

Weights

≈ 24.8 GB

Mac memory

32 GB+

apache-2.0 · updated 2025-07-29

deepseek-vl2-tiny-3bit

mlx-community/deepseek-vl2-tiny-3bit

3-bit

Vision + text ↓ 69 · ♥ 0

Params

3.4B

Weights

≈ 1.7 GB

Mac memory

8 GB+

deepseek · updated 2024-12-22

llm-jp-3-13b-instruct3

from llm-jp/llm-jp-3-13b-instruct3

Text generation · llm-jp ↓ 69 · ♥ 0

Params

14B

Weights

≈ 27.4 GB

Mac memory

48 GB+

apache-2.0 · updated 2025-02-05

magnum-v4-123b-4bit

from anthracite-org/magnum-v4-123b

4-bit

Text generation · anthracite-org ↓ 69 · ♥ 0

Params

123B

Weights

≈ 69.0 GB

Mac memory

96 GB+

mrl · updated 2024-12-18

gemma-3n-E2B-4bit

from google/gemma-3n-E4B

4-bit

Vision + text · Google · Gemma ↓ 68 · ♥ 4

Params

5.4B

Weights

≈ 4.5 GB

Mac memory

8 GB+

gemma · updated 2026-01-21

GLM-4.5-Air-6bit

from zai-org/GLM-4.5-Air

6-bit

Text generation · zai-org ↓ 68 · ♥ 3

Params

107B

Weights

≈ 86.8 GB

Mac memory

128 GB+

mit · updated 2025-07-28

Writer-Palmyra-Fin-70B-32K

mlx-community/Writer-Palmyra-Fin-70B-32K

Uncategorised ↓ 68 · ♥ 3

Params

71B

Weights

≈ 282 GB

Mac memory

512 GB+

writer-open-model-license · updated 2024-08-04

dhara-250m-OptiQ-8bit

from codelion/dhara-250m

8-bit

Text generation · codelion ↓ 68 · ♥ 3

Params

249M

Weights

≈ 356 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-07-12

Mellum-4b-base

from JetBrains/Mellum-4b-base

Text generation · JetBrains ↓ 68 · ♥ 2

Params

4.0B

Weights

≈ 8.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-06-28

Mistral-Nemo-Instruct-2407-bf16

mlx-community/Mistral-Nemo-Instruct-2407-bf16

bf16

Uncategorised ↓ 68 · ♥ 2

Params

12B

Weights

≈ 24.5 GB

Mac memory

32 GB+

apache-2.0 · updated 2024-11-06

TinyLlama-1.1B-Chat-v0.6

from TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T

Uncategorised · TinyLlama ↓ 68 · ♥ 2

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2023-12-24

dolphin-2.9-llama3-8b-4bit

from meta-llama/Meta-Llama-3-8B

4-bit

Uncategorised · Meta · Llama ↓ 68 · ♥ 2

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

other · updated 2024-04-21

Florence-2-base-ft-8bit

mlx-community/Florence-2-base-ft-8bit

8-bit

Vision + text ↓ 68 · ♥ 1

Params

271M

Weights

≈ 295 MB

Mac memory

8 GB+

mit · updated 2024-11-21

Hy-MT2-7B-bf16

from Tencent-Hunyuan/Hy-MT2-7B

bf16

Translation · Tencent-Hunyuan ↓ 68 · ♥ 1

Params

7.5B

Weights

≈ 15.0 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-05-31

Kimi-Linear-48B-A3B-Instruct-mlx-bf16

from moonshotai/Kimi-Linear-48B-A3B-Instruct

bf16

Text generation · Moonshot · Kimi ↓ 68 · ♥ 1

Params

49B

Weights

≈ 98.2 GB

Mac memory

128 GB+

mit · updated 2026-01-22

MiniCPM4-8B-4bit

from openbmb/MiniCPM4-8B

4-bit

Text generation · openbmb ↓ 68 · ♥ 1

Params

8.2B

Weights

≈ 4.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-06-09

Mistral-7B-Instruct-v0.1-4bit-mlx

mlx-community/Mistral-7B-Instruct-v0.1-4bit-mlx

4-bit

Text generation ↓ 68 · ♥ 1

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-04

Phi-4-mini-reasoning-6bit

from microsoft/Phi-4-mini-reasoning

6-bit

Text generation · Microsoft · Phi ↓ 68 · ♥ 1

Params

3.8B

Weights

≈ 3.1 GB

Mac memory

8 GB+

mit · updated 2025-05-01

gemma-2-9b-it-6bit

from google/gemma-2-9b-it

6-bit

Text generation · Google · Gemma ↓ 68 · ♥ 1

Params

9.2B

Weights

≈ 7.5 GB

Mac memory

16 GB+

gemma · updated 2025-03-06

gemma-3-12b-pt-4bit

from google/gemma-3-12b

4-bit

Vision + text · Google · Gemma ↓ 68 · ♥ 1

Params

—

Weights

—

Mac memory

—

gemma · updated 2025-03-18

pixtral-12b-bf16

mlx-community/pixtral-12b-bf16

bf16

Vision + text ↓ 68 · ♥ 1

Params

13B

Weights

≈ 25.4 GB

Mac memory

32 GB+

updated 2024-10-05

3b-fr-ft-research_release-bf16

from canopylabs/orpheus-3b-0.1-pretrained

bf16

Text to speech · canopylabs ↓ 68 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-04-09

3b-ko-ft-research_release-8bit

from canopylabs/orpheus-3b-0.1-pretrained

8-bit

Text to speech · canopylabs ↓ 68 · ♥ 0

Params

3.3B

Weights

≈ 3.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-09

DeepSeek-V4-Flash-5bit

mlx-community/DeepSeek-V4-Flash-5bit

5-bit

Text generation ↓ 68 · ♥ 0

Params

284B

Weights

≈ 196 GB

Mac memory

256 GB+

updated 2026-04-25

Kestrel-4B-Coder-6bit

from unsloth/Qwen3.5-4B

6-bit

Vision + text · unsloth ↓ 68 · ♥ 0

Params

4.5B

Weights

≈ 4.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-11-07

Llama-3-ELYZA-JP-8B-8bit

mlx-community/Llama-3-ELYZA-JP-8B-8bit

8-bit

Text generation ↓ 68 · ♥ 0

Params

8.0B

Weights

≈ 8.5 GB

Mac memory

16 GB+

llama3 · updated 2024-06-26

MiniCPM-V-4.6-8bit

from openbmb/MiniCPM-V-4.6

8-bit

Vision + text · openbmb ↓ 68 · ♥ 0

Params

1.3B

Weights

≈ 2.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-05-13

Nex-N2.5-mini-oQ4

from nex-agi/Nex-N2.5-mini

4-bit

Text generation · nex-agi ↓ 68 · ♥ 0

Params

35B

Weights

≈ 19.5 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-09-11

Phi-4-reasoning-4bit

from microsoft/Phi-4-reasoning

4-bit

Text generation · Microsoft · Phi ↓ 68 · ♥ 0

Params

15B

Weights

≈ 8.2 GB

Mac memory

16 GB+

mit · updated 2025-05-01

Unlimited-OCR-6bit

from baidu/Unlimited-OCR

6-bit

Vision + text · baidu ↓ 68 · ♥ 0

Params

3.3B

Weights

≈ 3.2 GB

Mac memory

8 GB+

mit · updated 2026-07-31

distilgpt2

from distilbert/distilgpt2

Text generation · distilbert ↓ 68 · ♥ 0

Params

82M

Weights

≈ 164 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-06-27

whisper-medium.en-mlx-8bit

mlx-community/whisper-medium.en-mlx-8bit

8-bit

Uncategorised ↓ 68 · ♥ 0

Params

—

Weights

—

Mac memory

—

updated 2024-03-09

Hunyuan-A52B-Instruct-3bit

from tencent-community/Hunyuan-A52B-Instruct

3-bit

Text generation · tencent-community ↓ 67 · ♥ 5

Params

389B

Weights

≈ 170 GB

Mac memory

256 GB+

updated 2024-11-23

Mixtral-8x7B-v0.1-hf-4bit-mlx

mlx-community/Mixtral-8x7B-v0.1-hf-4bit-mlx

4-bit

Uncategorised ↓ 67 · ♥ 5

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-27

Nous-Hermes-2-Mistral-7B-DPO-4bit-MLX

from mistralai/Mistral-7B-v0.1

4-bit

Uncategorised · Mistral ↓ 67 · ♥ 5

Params

7.2B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-02-21

DeepSeek-R1-Distill-Llama-8B-bf16

from deepseek-ai/DeepSeek-R1-Distill-Llama-8B

bf16

Uncategorised · DeepSeek ↓ 67 · ♥ 3

Params

8.0B

Weights

≈ 16.1 GB

Mac memory

24 GB+

updated 2025-02-26

Phi-3-vision-128k-instruct-8bit

mlx-community/Phi-3-vision-128k-instruct-8bit

8-bit

Text generation ↓ 67 · ♥ 3

Params

4.1B

Weights

≈ 4.4 GB

Mac memory

8 GB+

mit · updated 2024-06-24

DeepSeek-R1-Distill-Qwen-7B-bf16

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

bf16

Uncategorised · DeepSeek ↓ 67 · ♥ 2

Params

7.6B

Weights

≈ 15.2 GB

Mac memory

24 GB+

updated 2025-02-26

VoxCPM1.5-8bit

from openbmb/MiniCPM4-0.5B

8-bit

Text to speech · openbmb ↓ 67 · ♥ 2

Params

888M

Weights

≈ 1.0 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-12-16

codegemma-1.1-2b-8bit

from google/codegemma-1.1-2b

8-bit

Text generation · Google · Gemma ↓ 67 · ♥ 2

Params

2.5B

Weights

≈ 2.7 GB

Mac memory

8 GB+

gemma · updated 2025-06-02

meta-llama-Llama-4-Scout-17B-16E-fp16

from meta-llama/Llama-4-Scout-17B-16E

fp16

Text generation · Meta · Llama ↓ 67 · ♥ 2

Params

108B

Weights

≈ 216 GB

Mac memory

256 GB+

llama4 · updated 2025-04-06

MOSS-Music-8B-Thinking-6bit

from OpenMOSS-Team/MOSS-Music-8B-Thinking

6-bit

Audio + text · OpenMOSS-Team ↓ 67 · ♥ 1

Params

9.1B

Weights

≈ 8.1 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-06-28

Meta-Llama-3.1-70B-4bit

mlx-community/Meta-Llama-3.1-70B-4bit

4-bit

Text generation ↓ 67 · ♥ 1

Params

71B

Weights

≈ 39.7 GB

Mac memory

48 GB+

llama3.1 · updated 2024-07-23

Qwen3-30B-A3B-Instruct-2507-5bit

from Qwen/Qwen3-30B-A3B-Instruct-2507

5-bit

Text generation · Qwen ↓ 67 · ♥ 1

Params

31B

Weights

≈ 21.0 GB

Mac memory

32 GB+

apache-2.0 · updated 2025-07-29

gemma-4-31B-it-qat-assistant-mxfp8

from google/gemma-4-31B-it-qat-q4_0-unquantized-assistant

MXFP8

Text generation · Google · Gemma ↓ 67 · ♥ 1

Params

470M

Weights

≈ 499 MB

Mac memory

8 GB+

gemma · updated 2026-06-05

Bio-Medical-Llama-3-8B

from ContactDoctor/Bio-Medical-Llama-3-8B

4-bit

Text generation · ContactDoctor ↓ 67 · ♥ 0

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

other · updated 2025-01-26

Qwen2-VL-7B-Instruct-abliterated-4bit

from Qwen/Qwen2-VL-7B-Instruct

4-bit

Vision + text · Qwen ↓ 67 · ♥ 0

Params

8.3B

Weights

≈ 4.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-03-24

Ring-mini-2.0-4bit

from inclusionAI/Ring-mini-2.0

4-bit

Text generation · inclusionAI ↓ 67 · ♥ 0

Params

16B

Weights

≈ 9.1 GB

Mac memory

16 GB+

mit · updated 2025-09-15

UI-Venus-1.5-2B-6bit

from inclusionAI/UI-Venus-1.5-2B

6-bit

Vision + text · inclusionAI ↓ 67 · ♥ 0

Params

2.4B

Weights

≈ 2.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-20

deepseek-vl2-small-8bit

mlx-community/deepseek-vl2-small-8bit

8-bit

Vision + text ↓ 67 · ♥ 0

Params

16B

Weights

≈ 17.3 GB

Mac memory

24 GB+

deepseek · updated 2024-12-22

granite-8b-code-instruct-8bit

from ibm-granite/granite-8b-code-base-4k

8-bit

Text generation · IBM · Granite ↓ 67 · ♥ 0

Params

8.1B

Weights

≈ 8.6 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-05-06

snowflake-arctic-embed-l-v2.0-6bit

mlx-community/snowflake-arctic-embed-l-v2.0-6bit

6-bit

Sentence similarity ↓ 67 · ♥ 0

Params

568M

Weights

≈ 462 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-02

text-to-cypher-Gemma-3-4B-Instruct-MLX-FP16

from neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0

fp16

Uncategorised · neo4j ↓ 67 · ♥ 0

Params

3.9B

Weights

≈ 7.8 GB

Mac memory

16 GB+

gemma · updated 2025-11-09

whisper-base-asr-4bit

mlx-community/whisper-base-asr-4bit

4-bit

Speech recognition ↓ 67 · ♥ 0

Params

72M

Weights

≈ 42 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-01-15

gemma-3-27b-it-bf16

from google/gemma-3-27b-pt

bf16

Vision + text · Google · Gemma ↓ 66 · ♥ 5

Params

—

Weights

—

Mac memory

—

gemma · updated 2025-03-19

gemma-4-26b-a4b-nvfp4

from google/gemma-4-26b-a4b

4-bit

Vision + text · Google · Gemma ↓ 66 · ♥ 5

Params

26B

Weights

≈ 15.3 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-04-03

idefics2-8b-4bit

mlx-community/idefics2-8b-4bit

4-bit

Vision + text ↓ 66 · ♥ 3

Params

8.4B

Weights

≈ 4.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-01-29

IBM-granite-3.2-2b-instruct-4bit

mlx-community/IBM-granite-3.2-2b-instruct-4bit

4-bit

Uncategorised ↓ 66 · ♥ 2

Params

2.5B

Weights

≈ 1.4 GB

Mac memory

8 GB+

updated 2025-03-03

TinyLlama-1.1B-Chat-v1.0-mlx

mlx-community/TinyLlama-1.1B-Chat-v1.0-mlx

Uncategorised ↓ 66 · ♥ 2

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-14

Mistral7B-PairRM-SPPO-Iter3-unquantized

mlx-community/Mistral7B-PairRM-SPPO-Iter3-unquantized

Text generation ↓ 66 · ♥ 1

Params

7.2B

Weights

≈ 14.5 GB

Mac memory

24 GB+

apache-2.0 · updated 2024-05-07