Apple MLX models

Sky-T1-32B-Preview

from NovaSky-AI/Sky-T1-32B-Preview

Text generation · NovaSky-AI ↓ 55 · ♥ 0

Params

33B

Weights

≈ 65.5 GB

Mac memory

96 GB+

updated 2025-01-13

aya-expanse-8b-4bit-mlx

from CohereLabs/aya-expanse-8b

4-bit

Text generation · Cohere ↓ 55 · ♥ 0

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

cc-by-nc-4.0 · updated 2024-12-23

face-parsing-bisenet-bf16

from TMElyralab/MuseTalk

bf16

Image segmentation · TMElyralab ↓ 55 · ♥ 0

Params

13M

Weights

≈ 27 MB

Mac memory

8 GB+

mit · updated 2026-06-14

gemma-3-4b-pt-8bit

mlx-community/gemma-3-4b-pt-8bit

8-bit

Vision + text ↓ 55 · ♥ 0

Params

5.0B

Weights

≈ 5.7 GB

Mac memory

16 GB+

gemma · updated 2025-03-18

gemma-3n-E4B-it-5bit

from google/gemma-3n-E4B

5-bit

Vision + text · Google · Gemma ↓ 55 · ♥ 0

Params

—

Weights

—

Mac memory

—

gemma · updated 2025-07-12

granite-4.0-350m-8bit

from ibm-granite/granite-4.0-350m

8-bit

Text generation · IBM · Granite ↓ 55 · ♥ 0

Params

352M

Weights

≈ 374 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-28

granite-8b-code-base-4bit

mlx-community/granite-8b-code-base-4bit

4-bit

Text generation ↓ 55 · ♥ 0

Params

8.1B

Weights

≈ 4.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-05-06

rinna-llama-3-youko-8b-instruct-4bit

from rinna/llama-3-youko-8b-instruct

4-bit

Uncategorised · rinna ↓ 55 · ♥ 0

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

llama3 · updated 2024-10-22

Meta-Llama-3-8B-8bit

mlx-community/Meta-Llama-3-8B-8bit

8-bit

Text generation ↓ 54 · ♥ 5

Params

8.0B

Weights

≈ 9.0 GB

Mac memory

16 GB+

llama3 · updated 2024-04-18

nanoLLaVA

mlx-community/nanoLLaVA

Uncategorised ↓ 54 · ♥ 5

Params

1.1B

Weights

≈ 2.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-12-26

MiniCPM-2B-sft-bf16-llama-format-mlx

mlx-community/MiniCPM-2B-sft-bf16-llama-format-mlx

bf16

Uncategorised ↓ 54 · ♥ 3

Params

—

Weights

—

Mac memory

—

updated 2024-02-20

Qwen2-VL-2B-4bit

mlx-community/Qwen2-VL-2B-4bit

4-bit

Vision + text ↓ 54 · ♥ 3

Params

2.2B

Weights

≈ 1.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-03-24

Qwen3.5-9B-Fable-5-v1-oQ8

mlx-community/Qwen3.5-9B-Fable-5-v1-oQ8

8-bit

Uncategorised ↓ 54 · ♥ 3

Params

9.4B

Weights

≈ 10.4 GB

Mac memory

16 GB+

updated 2026-07-03

GLM-4.5-Air-mxfp4

from zai-org/GLM-4.5-Air

MXFP4

Text generation · zai-org ↓ 54 · ♥ 2

Params

107B

Weights

≈ 60.1 GB

Mac memory

96 GB+

mit · updated 2025-09-26

Llama-3_3-Nemotron-Super-49B-v1-mlx-4bit

from nvidia/Llama-3_3-Nemotron-Super-49B-v1

4-bit

Text generation · NVIDIA ↓ 54 · ♥ 2

Params

50B

Weights

≈ 28.1 GB

Mac memory

48 GB+

nvidia-open-model-license · updated 2025-04-08

llava-v1.6-34b-8bit

mlx-community/llava-v1.6-34b-8bit

8-bit

Vision + text ↓ 54 · ♥ 2

Params

35B

Weights

≈ 36.9 GB

Mac memory

48 GB+

updated 2024-10-06

sapiens2-seg-0.4b-bf16

from facebook/sapiens2-seg-0.4b

bf16

Image to image · facebook ↓ 54 · ♥ 2

Params

407M

Weights

≈ 813 MB

Mac memory

8 GB+

sapiens2-license · updated 2026-04-24

Arcee-Blitz-4bit

from arcee-ai/Arcee-Blitz

4-bit

Text generation · arcee-ai ↓ 54 · ♥ 1

Params

24B

Weights

≈ 13.3 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-02-20

DeepSeek-V3-0324-5bit

from deepseek-ai/DeepSeek-V3-0324

5-bit

Text generation · DeepSeek ↓ 54 · ♥ 1

Params

671B

Weights

≈ 461 GB

Mac memory

> 512 GB

mit · updated 2025-07-06

Hunyuan-1.8B-Instruct-4bit

from tencent/Hunyuan-1.8B-Instruct

4-bit

Text generation · tencent ↓ 54 · ♥ 1

Params

1.8B

Weights

≈ 1.0 GB

Mac memory

8 GB+

updated 2025-08-04

Mistral-Nemo-Instruct-2407-3bit

from mistralai/Mistral-Nemo-Instruct-2407

3-bit

Uncategorised · Mistral ↓ 54 · ♥ 1

Params

12B

Weights

≈ 5.4 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-01-09

Qwen3-0.6B-gabliterated-4bit

from Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated

4-bit

Text generation · Goekdeniz-Guelmez ↓ 54 · ♥ 1

Params

596M

Weights

≈ 335 MB

Mac memory

8 GB+

updated 2026-01-06

Qwen3-30B-A3B-Instruct-2507-4bit-DWQ

mlx-community/Qwen3-30B-A3B-Instruct-2507-4bit-DWQ

4-bit DWQ

Uncategorised ↓ 54 · ♥ 1

Params

31B

Weights

≈ 6.0 GB

Mac memory

16 GB+

updated 2025-07-30

Qwen3-VL-2B-Instruct-6bit

mlx-community/Qwen3-VL-2B-Instruct-6bit

6-bit

Vision + text ↓ 54 · ♥ 1

Params

2.1B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-21

Qwen3-VL-8B-Thinking-8bit

mlx-community/Qwen3-VL-8B-Thinking-8bit

8-bit

Vision + text ↓ 54 · ♥ 1

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-10-14

codegemma-1.1-2b-6bit

from google/codegemma-1.1-2b

6-bit

Text generation · Google · Gemma ↓ 54 · ♥ 1

Params

2.5B

Weights

≈ 2.0 GB

Mac memory

8 GB+

gemma · updated 2025-06-01

dolphin-2.8-mistral-7b-v02

from mistral-community/Mistral-7B-v0.2

Uncategorised · mistral-community ↓ 54 · ♥ 1

Params

7.2B

Weights

≈ 14.5 GB

Mac memory

24 GB+

apache-2.0 · updated 2024-04-06

paligemma2-3b-pt-896-4bit

mlx-community/paligemma2-3b-pt-896-4bit

4-bit

Vision + text ↓ 54 · ♥ 1

Params

3.0B

Weights

≈ 1.7 GB

Mac memory

8 GB+

gemma · updated 2024-12-06

3b-fr-pretrain-research_release-8bit

from meta-llama/Llama-3.2-3B-Instruct

8-bit

Text to speech · Meta · Llama ↓ 54 · ♥ 0

Params

3.3B

Weights

≈ 3.5 GB

Mac memory

8 GB+

llama3.2 · updated 2025-04-09

Deutscher-Pantheon-12B-4bit

from mergekit-community/Deutscher-Pantheon-12B

4-bit

Text generation · mergekit-community ↓ 54 · ♥ 0

Params

12B

Weights

≈ 6.9 GB

Mac memory

16 GB+

updated 2025-06-03

Dolphin3.0-R1-Mistral-24B-6bit

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

6-bit

Text generation · dphn ↓ 54 · ♥ 0

Params

24B

Weights

≈ 19.2 GB

Mac memory

24 GB+

updated 2025-03-06

EuroLLM-22B-Instruct-2512-mlx-6bit

from utter-project/EuroLLM-22B-Instruct-2512

6-bit

Text generation · utter-project ↓ 54 · ♥ 0

Params

23B

Weights

≈ 18.4 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-12-16

GLM-4.5-Air-5bit

from zai-org/GLM-4.5-Air

5-bit

Text generation · zai-org ↓ 54 · ♥ 0

Params

107B

Weights

≈ 73.5 GB

Mac memory

96 GB+

mit · updated 2025-07-28

GLM-4.6V-nvfp4

from zai-org/GLM-4.6V

4-bit

Vision + text · zai-org ↓ 54 · ♥ 0

Params

108B

Weights

≈ 61.9 GB

Mac memory

96 GB+

mit · updated 2026-03-05

Goedel-Prover-V2-32B-8bit

from Goedel-LM/Goedel-Prover-V2-32B

8-bit

Text generation · Goedel-LM ↓ 54 · ♥ 0

Params

33B

Weights

≈ 34.8 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-01-26

Jan-nano-128k-8bit

from Menlo/Jan-nano-128k

8-bit

Text generation · Menlo ↓ 54 · ♥ 0

Params

4.0B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-06-26

Llama-3-Aplite-Instruct-4x8B-MoE-4bit

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

4-bit

Text generation · Meta · Llama ↓ 54 · ♥ 0

Params

25B

Weights

≈ 14.0 GB

Mac memory

24 GB+

llama3 · updated 2024-04-26

Llama-3.2-11B-Vision-Surgical-CholecT50-8bit

mlx-community/Llama-3.2-11B-Vision-Surgical-CholecT50-8bit

8-bit

Uncategorised ↓ 54 · ♥ 0

Params

—

Weights

—

Mac memory

—

nvidia-community-model-license · updated 2025-06-04

Mistral-7B-v0.1-q

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

Text generation ↓ 54 · ♥ 0

Params

7.2B

Weights

≈ 28.7 GB

Mac memory

48 GB+

apache-2.0 · updated 2024-02-25

Qwen3-4B-Instruct-2507-gabliterated-6bit

from Goekdeniz-Guelmez/Qwen3-4B-Instruct-2507-gabliterated

6-bit

Text generation · Goekdeniz-Guelmez ↓ 54 · ♥ 0

Params

4.0B

Weights

≈ 3.3 GB

Mac memory

8 GB+

updated 2026-01-06

Qwen3-4B-Sky-High-Hermes-gabliterated-8bit

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

8-bit

Text generation · Goekdeniz-Guelmez ↓ 54 · ♥ 0

Params

4.0B

Weights

≈ 4.3 GB

Mac memory

8 GB+

updated 2026-01-23

ShowUI-2B-bf16-4bit

from Qwen/Qwen2-VL-2B-Instruct

4-bit

Uncategorised · Qwen ↓ 54 · ♥ 0

Params

2.2B

Weights

≈ 2.2 GB

Mac memory

8 GB+

mit · updated 2025-02-26

SmolLM3-3B-abliterated-bf16

from HuggingFaceTB/SmolLM3-3B

bf16

Text generation · Hugging Face ↓ 54 · ♥ 0

Params

3.1B

Weights

≈ 6.2 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-07-10

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

from google/gemma-3-12b-pt

4-bit

Text generation · Google · Gemma ↓ 54 · ♥ 0

Params

12B

Weights

≈ 6.6 GB

Mac memory

16 GB+

gemma · updated 2026-02-23

gemma-3n-E2B-it-3bit

from google/gemma-3n-E4B-it

3-bit

Vision + text · Google · Gemma ↓ 54 · ♥ 0

Params

5.4B

Weights

≈ 3.9 GB

Mac memory

8 GB+

gemma · updated 2025-07-06

gemma-4-31B-it-qat-mxfp4

mlx-community/gemma-4-31B-it-qat-mxfp4

MXFP4

Vision + text ↓ 54 · ♥ 0

Params

31B

Weights

≈ 18.4 GB

Mac memory

24 GB+

updated 2026-06-05

perplexity-ai-r1-1776-8bit

from perplexity-ai/r1-1776

8-bit

Uncategorised · perplexity-ai ↓ 54 · ♥ 0

Params

671B

Weights

≈ 713 GB

Mac memory

> 512 GB

mit · updated 2025-02-25

whisper-tiny-asr-4bit

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

4-bit

Speech recognition ↓ 54 · ♥ 0

Params

37M

Weights

≈ 22 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-01-15

LFM2-VL-1.6B-8bit

mlx-community/LFM2-VL-1.6B-8bit

8-bit

Vision + text ↓ 53 · ♥ 10

Params

1.6B

Weights

≈ 2.1 GB

Mac memory

8 GB+

lfm1.0 · updated 2025-12-20

Qwen3-30B-A3B-4bit-DWQ-05082025

from Qwen/Qwen3-30B-A3B

4-bit DWQ

Text generation · Qwen ↓ 53 · ♥ 4

Params

31B

Weights

≈ 17.2 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-05-08

Agents-A1-5bit

from InternScience/Agents-A1

5-bit

Vision + text · InternScience ↓ 53 · ♥ 3

Params

35B

Weights

≈ 24.7 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-07-01

DeepSeek-R1

from deepseek-ai/DeepSeek-R1

8-bit

Uncategorised · DeepSeek ↓ 53 · ♥ 3

Params

—

Weights

—

Mac memory

—

mit · updated 2025-05-05

gemma-3-27b-it-4bit-DWQ

from google/gemma-3-27b-it

4-bit DWQ

Text generation · Google · Gemma ↓ 53 · ♥ 3

Params

28B

Weights

≈ 16.0 GB

Mac memory

24 GB+

gemma · updated 2025-05-14

granite-4.0-h-tiny-5bit-MLX

from ibm-granite/granite-4.0-h-tiny

5-bit

Text generation · IBM · Granite ↓ 53 · ♥ 2

Params

6.9B

Weights

≈ 4.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-03

mxbai-rerank-large-v2

from mixedbread-ai/mxbai-rerank-large-v2

Text generation · mixedbread-ai ↓ 53 · ♥ 2

Params

1.5B

Weights

≈ 3.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-07-23

3b-hi-ft-research_release-8bit

from canopylabs/orpheus-3b-0.1-pretrained

8-bit

Text to speech · canopylabs ↓ 53 · ♥ 1

Params

3.3B

Weights

≈ 3.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-09

Apertus-8B-Instruct-2509-6bit

from swiss-ai/Apertus-8B-Instruct-2509

6-bit

Text generation · swiss-ai ↓ 53 · ♥ 1

Params

8.1B

Weights

≈ 6.5 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-09-03

Falcon3-7B-Instruct-1.58bit-4bit

from tiiuae/Falcon3-7B-Instruct-1.58bit

58-bit

Text generation · TII · Falcon ↓ 53 · ♥ 1

Params

3.5B

Weights

≈ 3.8 GB

Mac memory

8 GB+

falcon-llm-license · updated 2025-06-10

Llama-3.1-Tulu-3-8B-8bit

from allenai/Llama-3.1-Tulu-3-8B

8-bit

Text generation · Ai2 · OLMo ↓ 53 · ♥ 1

Params

8.0B

Weights

≈ 8.5 GB

Mac memory

16 GB+

llama3.1 · updated 2024-11-25

Meta-Llama-3.1-8B-bf16

mlx-community/Meta-Llama-3.1-8B-bf16

bf16

Text generation ↓ 53 · ♥ 1

Params

8.0B

Weights

≈ 16.1 GB

Mac memory

24 GB+

llama3.1 · updated 2024-07-23