Apple MLX models

GLM-4.5V-abliterated-4bit

from zai-org/GLM-4.5V

4-bit

Vision + text · zai-org ↓ 77 · ♥ 1

Params

—

Weights

—

Mac memory

—

mit · updated 2025-09-05

kitten-tts-nano-0.8-8bit

mlx-community/kitten-tts-nano-0.8-8bit

8-bit

Text to speech ↓ 77 · ♥ 1

Params

15M

Weights

≈ 38 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-02-24

orpheus-3b-0.1-ft-6bit

from canopylabs/orpheus-3b-0.1-ft

6-bit

Text to speech · canopylabs ↓ 77 · ♥ 1

Params

3.3B

Weights

≈ 2.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-03-21

Hunyuan-MT-7B-8bit

from tencent/Hunyuan-MT-7B

8-bit

Text generation · tencent ↓ 77 · ♥ 0

Params

7.5B

Weights

≈ 8.0 GB

Mac memory

16 GB+

updated 2026-06-13

Josiefied-Qwen3-4B-Instruct-2507-abliterated-v1-4bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-4B-Instruct-2507-abliterated-v1

4-bit

Text generation · Goekdeniz-Guelmez ↓ 77 · ♥ 0

Params

4.0B

Weights

≈ 2.3 GB

Mac memory

8 GB+

updated 2025-10-29

MiMo-VL-7B-RL-bf16

from XiaomiMiMo/MiMo-VL-7B-RL

bf16

Vision + text · XiaomiMiMo ↓ 77 · ♥ 0

Params

8.3B

Weights

≈ 16.6 GB

Mac memory

24 GB+

mit · updated 2025-05-31

Qwen3-14B-Ja-Fin-Thinking-v0.1-MLX-4bit

from nri-ai/Qwen3-14B-Ja-Fin-Thinking

4-bit

Text generation · nri-ai ↓ 77 · ♥ 0

Params

15B

Weights

≈ 8.3 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-27

Qwen3-VL-8B-Instruct-3bit

mlx-community/Qwen3-VL-8B-Instruct-3bit

3-bit

Vision + text ↓ 77 · ♥ 0

Params

8.8B

Weights

≈ 4.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-14

deepseek-vl2-small-6bit

mlx-community/deepseek-vl2-small-6bit

6-bit

Vision + text ↓ 77 · ♥ 0

Params

16B

Weights

≈ 13.3 GB

Mac memory

24 GB+

deepseek · updated 2024-12-22

snowflake-arctic-embed-l-v2.0-4bit

mlx-community/snowflake-arctic-embed-l-v2.0-4bit

4-bit

Sentence similarity ↓ 77 · ♥ 0

Params

568M

Weights

≈ 320 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-02

gemma-1.1-7b-it-4bit

mlx-community/gemma-1.1-7b-it-4bit

4-bit

Text generation ↓ 76 · ♥ 4

Params

8.5B

Weights

≈ 5.9 GB

Mac memory

16 GB+

gemma · updated 2024-04-08

Qwen2-7B-Instruct-4bit

mlx-community/Qwen2-7B-Instruct-4bit

4-bit

Text generation ↓ 76 · ♥ 3

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-06-06

Qwen2-VL-2B-mlx

from Qwen/Qwen2-VL-2B

Vision + text · Qwen ↓ 76 · ♥ 3

Params

2.2B

Weights

≈ 4.4 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-09-21

medgemma-27b-it-bf16

from google/gemma-3-27b-pt

bf16

Vision + text · Google · Gemma ↓ 76 · ♥ 3

Params

—

Weights

—

Mac memory

—

health-ai-developer-foundations · updated 2025-07-10

Mamba-Codestral-7B-v0.1

from mistralai/Mamba-Codestral-7B-v0.1

Uncategorised · Mistral ↓ 76 · ♥ 2

Params

7.3B

Weights

≈ 14.6 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-01-21

Qwen3-4B-ARC-MLX-4bit

from sorokin/qwen3_4b_grids15_sft139

4-bit

Text generation · sorokin ↓ 76 · ♥ 2

Params

3.6B

Weights

≈ 2.0 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-04

c4ai-command-r-plus-08-2024-8bit

mlx-community/c4ai-command-r-plus-08-2024-8bit

8-bit

Text generation ↓ 76 · ♥ 2

Params

104B

Weights

≈ 110 GB

Mac memory

128 GB+

cc-by-nc-4.0 · updated 2024-08-31

1.5-Pints-16K-v0.1

from pints-ai/1.5-Pints-16K-v0.1

Text generation · pints-ai ↓ 76 · ♥ 1

Params

1.6B

Weights

≈ 3.1 GB

Mac memory

8 GB+

mit · updated 2024-10-28

LongCat-Flash-Lite-Sparse-4bit

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

4-bit

Text generation · meituan-longcat ↓ 76 · ♥ 1

Params

69B

Weights

≈ 38.6 GB

Mac memory

48 GB+

mit · updated 2026-08-31

Mamba-Codestral-7B-v0.1-4bit

from mistralai/Mamba-Codestral-7B-v0.1

4-bit

Uncategorised · Mistral ↓ 76 · ♥ 1

Params

1.1B

Weights

≈ 975 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-01-21

North-Micro-Vision-Instruct-4bit

from CohereLabs/North-Micro-Vision-Instruct

4-bit

Vision + text · Cohere ↓ 76 · ♥ 1

Params

2.5B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-08-12

gemma-3-270m-it-qat-4bit

from google/gemma-3-270m-it-qat

4-bit

Text generation · Google · Gemma ↓ 76 · ♥ 1

Params

436M

Weights

≈ 245 MB

Mac memory

8 GB+

gemma · updated 2025-08-09

Falcon-H1-0.5B-Instruct-4bit

from tiiuae/Falcon-H1-0.5B-Instruct

4-bit

Text generation · TII · Falcon ↓ 76 · ♥ 0

Params

521M

Weights

≈ 294 MB

Mac memory

8 GB+

falcon-llm-license · updated 2025-09-26

Falcon-H1-7B-Instruct-4bit

from tiiuae/Falcon-H1-7B-Instruct

4-bit

Text generation · TII · Falcon ↓ 76 · ♥ 0

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

falcon-llm-license · updated 2025-09-29

Huihui-gemma-4-26B-A4B-it-qat-q4_0-unquantized-abliterated-4bit-msq

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

4-bit

Any to any · Google · Gemma ↓ 76 · ♥ 0

Params

26B

Weights

≈ 4.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-06-15

K-EXAONE-236B-A23B-6bit

from LGAI-EXAONE/K-EXAONE-236B-A23B

6-bit

Text generation · LGAI-EXAONE ↓ 76 · ♥ 0

Params

237B

Weights

≈ 192 GB

Mac memory

256 GB+

k-exaone · updated 2026-01-06

Qwen3-0.6B-Base-bf16

from Qwen/Qwen3-0.6B-Base

bf16

Text generation · Qwen ↓ 76 · ♥ 0

Params

596M

Weights

≈ 1.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-12-25

Qwen3-4B-Sky-High-Hermes-gabliterated-4bit

from Goekdeniz-Guelmez/Qwen3-4B-Sky-High-Hermes-gabliterated

4-bit

Text generation · Goekdeniz-Guelmez ↓ 76 · ♥ 0

Params

4.0B

Weights

≈ 2.3 GB

Mac memory

8 GB+

updated 2026-01-23

TinySwallow-1.5B-Instruct-4bit

from SakanaAI/TinySwallow-1.5B-Instruct

4-bit

Text generation · SakanaAI ↓ 76 · ♥ 0

Params

1.5B

Weights

≈ 869 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-01-30

deepseek-vl-7b-chat-8bit

mlx-community/deepseek-vl-7b-chat-8bit

8-bit

Vision + text ↓ 76 · ♥ 0

Params

7.3B

Weights

≈ 7.8 GB

Mac memory

16 GB+

deepseek · updated 2024-12-26

gemma-3n-E2B-it-bf16

from google/gemma-3n-E4B-it

bf16

Vision + text · Google · Gemma ↓ 76 · ♥ 0

Params

6.0B

Weights

≈ 10.9 GB

Mac memory

16 GB+

gemma · updated 2025-07-12

llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

mlx-community/llm-jp-13b-instruct-full-ac_001_16x-dolly-ichikara_004_001_single-oasst-oasst2-v2.0

Text generation ↓ 76 · ♥ 0

Params

14B

Weights

≈ 27.4 GB

Mac memory

48 GB+

apache-2.0 · updated 2024-04-30

GLM-4.5-Air-3bit-DWQ-v2

from zai-org/GLM-4.5-Air

3-bit DWQ

Text generation · zai-org ↓ 75 · ♥ 4

Params

107B

Weights

≈ 46.8 GB

Mac memory

64 GB+

mit · updated 2025-08-13

Qwen-AgentWorld-35B-A3B-bf16

from Qwen/Qwen-AgentWorld-35B-A3B

bf16

Text generation · Qwen ↓ 75 · ♥ 3

Params

35B

Weights

≈ 69.3 GB

Mac memory

96 GB+

apache-2.0 · updated 2026-06-27

sam-audio-base

from facebook/sam-audio-base

Audio to audio · facebook ↓ 75 · ♥ 2

Params

1.3B

Weights

≈ 5.0 GB

Mac memory

8 GB+

other · updated 2026-02-06

GLM-4.7-Flash-8bit-mxfp8

from zai-org/GLM-4.7-Flash

MXFP8

Text generation · zai-org ↓ 75 · ♥ 1

Params

30B

Weights

≈ 31.8 GB

Mac memory

48 GB+

mit · updated 2026-02-10

Ministral-3-14B-Instruct-2512-bf16

from mistralai/Ministral-3-14B-Base-2512

bf16

Uncategorised · Mistral ↓ 75 · ♥ 1

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-12-03

K2-Horizon-0.9B-bf16

from IFM/K2-Horizon-0.9B

bf16

Text generation · IFM ↓ 75 · ♥ 0

Params

1.1B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-09-30

Ministral-3-14B-Reasoning-2512-6bit

from mistralai/Ministral-3-14B-Base-2512

6-bit

Uncategorised · Mistral ↓ 75 · ♥ 0

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-12-04

Qwen2.5-7B-Instruct-1M-bf16

from Qwen/Qwen2.5-7B-Instruct-1M

bf16

Text generation · Qwen ↓ 75 · ♥ 0

Params

7.6B

Weights

≈ 15.2 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-01-26

Qwen3-VL-Reranker-2B-nvfp4

from Qwen/Qwen3-VL-2B-Instruct

Reranking · Qwen ↓ 75 · ♥ 0

Params

2.1B

Weights

≈ 7.7 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-14

granite-vision-3.2-2b-4bit

from ibm-granite/granite-vision-3.2-2b

4-bit

Vision + text · IBM · Granite ↓ 75 · ♥ 0

Params

3.1B

Weights

≈ 2.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-04-01

starcoder2-15b-instruct-v0.1-8bit

from bigcode/starcoder2-15b

8-bit

Text generation · BigCode ↓ 75 · ♥ 0

Params

16B

Weights

≈ 17.0 GB

Mac memory

24 GB+

bigcode-openrail-m · updated 2024-04-30

DiffuCoder-7B-cpGRPO-8bit

from apple/DiffuCoder-7B-cpGRPO

8-bit

Text generation · apple ↓ 74 · ♥ 9

Params

7.6B

Weights

≈ 8.1 GB

Mac memory

16 GB+

unknown · updated 2025-07-04

SmolVLM-Instruct-bf16

from HuggingFaceTB/SmolVLM-Instruct

bf16

Vision + text · Hugging Face ↓ 74 · ♥ 5

Params

2.2B

Weights

≈ 4.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-11-29

GLM-4.6V-Flash-bf16

mlx-community/GLM-4.6V-Flash-bf16

bf16

Vision + text ↓ 74 · ♥ 4

Params

10B

Weights

≈ 20.6 GB

Mac memory

32 GB+

mit · updated 2025-12-08

Hy3-preview-4bit

from tencent/Hy3-preview

4-bit

Text generation · tencent ↓ 74 · ♥ 4

Params

295B

Weights

≈ 166 GB

Mac memory

192 GB+

other · updated 2026-04-27

Qwen2-7B-Instruct-8bit

mlx-community/Qwen2-7B-Instruct-8bit

8-bit

Text generation ↓ 74 · ♥ 4

Params

7.6B

Weights

≈ 8.1 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-06-06

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

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

4-bit

Text generation ↓ 74 · ♥ 3

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2024-01-07

Ministral-8B-Instruct-2410-bf16

from Ministral-8B-Instruct-2410-HF

bf16

Uncategorised ↓ 74 · ♥ 2

Params

8.0B

Weights

≈ 16.0 GB

Mac memory

24 GB+

mrl · updated 2024-10-17

Josiefied-Qwen3-30B-A3B-abliterated-v2-8bit

from Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2

8-bit

Text generation · Goekdeniz-Guelmez ↓ 74 · ♥ 1

Params

31B

Weights

≈ 32.4 GB

Mac memory

48 GB+

updated 2025-06-19

Josiefied-Qwen3-8B-abliterated-v1-8bit

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

8-bit

Text generation · Goekdeniz-Guelmez ↓ 74 · ♥ 1

Params

8.2B

Weights

≈ 8.7 GB

Mac memory

16 GB+

updated 2025-05-02

Mistral-NeMo-Minitron-8B-Instruct-4bit

from nvidia/Mistral-NeMo-Minitron-8B-Base

4-bit

Text generation · NVIDIA ↓ 74 · ♥ 1

Params

8.4B

Weights

≈ 4.7 GB

Mac memory

8 GB+

nvidia-community-model-license · updated 2024-10-04

NAFNet-GoPro-width64

from megvii-research/NAFNet

Image to image · megvii-research ↓ 74 · ♥ 1

Params

68M

Weights

≈ 272 MB

Mac memory

8 GB+

mit · updated 2026-06-04

Nanbeige4.1-3B-4bit

from Nanbeige/Nanbeige4.1-3B

4-bit

Text generation · Nanbeige ↓ 74 · ♥ 1

Params

3.9B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-02-23

QwQ-Qwen2.5-Coder-Instruct-32B-4bit

from sm54/QwQ-Qwen2.5-Coder-Instruct-32B

4-bit

Text generation · sm54 ↓ 74 · ♥ 1

Params

33B

Weights

≈ 18.4 GB

Mac memory

24 GB+

updated 2025-03-09

Qwen3-30B-A3B-6bit

from Qwen/Qwen3-30B-A3B

6-bit

Text generation · Qwen ↓ 74 · ♥ 1

Params

31B

Weights

≈ 24.8 GB

Mac memory

32 GB+

apache-2.0 · updated 2025-04-28

SmolLM3-3B-4bit-DWQ

from HuggingFaceTB/SmolLM3-3B

4-bit DWQ

Text generation · Hugging Face ↓ 74 · ♥ 1

Params

3.1B

Weights

≈ 1.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-07-09

3b-es_it-ft-research_release-4bit

from canopylabs/orpheus-3b-0.1-pretrained

4-bit

Text to speech · canopylabs ↓ 74 · ♥ 0

Params

3.3B

Weights

≈ 1.9 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-09

Dracarys2-72B-Instruct-4bit

from abacusai/Dracarys2-72B-Instruct

4-bit

Text generation · abacusai ↓ 74 · ♥ 0

Params

73B

Weights

≈ 40.9 GB

Mac memory

48 GB+

tongyi-qianwen · updated 2024-10-06