Apple MLX models

olmOCR-2-7B-1025-mlx-8bit

from Qwen/Qwen2.5-VL-7B-Instruct

8-bit

Vision + text · Qwen ↓ 232K · ♥ 2

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-10-29

Qwen3.8-27B-4bit

from Qwen/Qwen3.8-27B

4-bit

Vision + text · Qwen ↓ 177K · ♥ 239

Params

27B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-11-11

Devstral-Small-2-24B-Instruct-2512-4bit

from mistralai/Devstral-Small-2-24B-Instruct-2512

4-bit

Vision + text · Mistral ↓ 72K · ♥ 13

Params

24B

Weights

≈ 15.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-07-04

Qwen3.5-0.8B-4bit

from Qwen/Qwen3.5-0.8B-Base

4-bit

Vision + text · Qwen ↓ 60K · ♥ 4

Params

853M

Weights

≈ 625 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-02

Qwen3.6-27B-4bit

from Qwen/Qwen3.6-27B

4-bit

Vision + text · Qwen ↓ 49K · ♥ 52

Params

27B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-04-22

gemma-3-4b-it-qat-4bit

from OpenGVLab/InternVL3-1B-Instruct

4-bit

Vision + text · OpenGVLab ↓ 42K · ♥ 9

Params

5.0B

Weights

≈ 3.0 GB

Mac memory

8 GB+

qwen · updated 2025-04-21

Qwen3.6-35B-A3B-4bit

from Qwen/Qwen3.6-35B-A3B

4-bit

Vision + text · Qwen ↓ 38K · ♥ 124

Params

35B

Weights

≈ 20.4 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-04-16

Qwen3.8-27B-8bit

from Qwen/Qwen3.8-27B

8-bit

Vision + text · Qwen ↓ 27K · ♥ 88

Params

27B

Weights

≈ 29.5 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-11-11

Qwen3.5-9B-MLX-4bit

from Qwen/Qwen3.5-9B

4-bit

Vision + text · Qwen ↓ 27K · ♥ 191

Params

9.4B

Weights

≈ 6.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-23

gemma-4-e4b-it-4bit

from google/gemma-4-E4B-it

4-bit

Vision + text · Google · Gemma ↓ 26K · ♥ 42

Params

7.9B

Weights

≈ 5.1 GB

Mac memory

8 GB+

gemma · updated 2026-07-06

Qwen3.5-9B-4bit

from Qwen/Qwen3.5-9B-Base

4-bit

Vision + text · Qwen ↓ 25K · ♥ 21

Params

9.4B

Weights

≈ 6.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-02

gemma-4-e2b-it-4bit

from google/gemma-4-E2B-it

4-bit

Vision + text · Google · Gemma ↓ 25K · ♥ 38

Params

5.1B

Weights

≈ 3.6 GB

Mac memory

8 GB+

gemma · updated 2026-07-06

Qwen2.5-VL-7B-Instruct-4bit

from Qwen/Qwen2.5-VL-7B-Instruct

4-bit

Vision + text · Qwen ↓ 21K · ♥ 6

Params

8.3B

Weights

≈ 5.6 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-02-25

Qwen2-VL-2B-Instruct-4bit

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

4-bit

Vision + text ↓ 21K · ♥ 7

Params

2.2B

Weights

≈ 1.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-03-24

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

from OpenGVLab/InternVL3-1B-Instruct

4-bit

Vision + text · OpenGVLab ↓ 20K · ♥ 24

Params

—

Weights

—

Mac memory

—

qwen · updated 2025-04-19

gemma-3-12b-it-qat-4bit

from OpenGVLab/InternVL3-1B-Instruct

4-bit

Vision + text · OpenGVLab ↓ 19K · ♥ 21

Params

—

Weights

—

Mac memory

—

qwen · updated 2025-04-21

Qwen3-VL-4B-Instruct-4bit

mlx-community/Qwen3-VL-4B-Instruct-4bit

4-bit

Vision + text ↓ 19K · ♥ 9

Params

4.4B

Weights

≈ 3.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-16

gemma-3-4b-it-8bit

from google/gemma-3-4b-pt

8-bit

Vision + text · Google · Gemma ↓ 18K · ♥ 6

Params

5.0B

Weights

≈ 5.7 GB

Mac memory

16 GB+

gemma · updated 2025-03-19

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

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

4-bit

Vision + text · Google · Gemma ↓ 17K · ♥ 89

Params

26B

Weights

≈ 15.3 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-07-05

gemma-4-E2B-it-qat-mobile

mlx-community/gemma-4-E2B-it-qat-mobile

8-bit

Vision + text ↓ 17K · ♥ 3

Params

2.3B

Weights

≈ 2.5 GB

Mac memory

8 GB+

updated 2026-07-29

gemma-3-12b-it-4bit

from google/gemma-3-12b-pt

4-bit

Vision + text · Google · Gemma ↓ 15K · ♥ 8

Params

—

Weights

—

Mac memory

—

gemma · updated 2025-03-19

gemma-4-E4B-it-qat-mobile

mlx-community/gemma-4-E4B-it-qat-mobile

8-bit

Vision + text ↓ 13K · ♥ 0

Params

3.4B

Weights

≈ 3.7 GB

Mac memory

8 GB+

updated 2026-08-11

Qwen3.5-2B-6bit

from Qwen/Qwen3.5-2B-Base

6-bit

Vision + text · Qwen ↓ 13K · ♥ 7

Params

2.2B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-02

Muse-Spark-Open-816B-A42B-4bit

from meta-models/Muse-Spark-Open-816B-A42B

4-bit

Vision + text · meta-models ↓ 9.6K · ♥ 8

Params

822B

Weights

≈ 533 GB

Mac memory

> 512 GB

muse-model-license · updated 2026-10-16

Muse-Glimmer-30B-4bit

from meta-models/Muse-Glimmer-30B

4-bit

Vision + text · meta-models ↓ 9.5K · ♥ 18

Params

30B

Weights

≈ 19.4 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-08-10

Qwen3.8-27B-OptiQ-4bit

from Qwen/Qwen3.8-27B

4-bit

Vision + text · Qwen ↓ 8.8K · ♥ 22

Params

27B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-10-30

gemma-4-12B-it-4bit

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

4-bit

Vision + text ↓ 8.7K · ♥ 17

Params

12B

Weights

≈ 6.7 GB

Mac memory

16 GB+

updated 2026-06-08

Qwen3.5-2B-4bit

from Qwen/Qwen3.5-2B-Base

4-bit

Vision + text · Qwen ↓ 8.6K · ♥ 6

Params

2.2B

Weights

≈ 1.7 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-02

DeepSeek-V4.1-Flash-1017-oQ4e-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017

Vision + text · DeepSeek ↓ 8.2K · ♥ 19

Params

129B

Weights

≈ 432 GB

Mac memory

512 GB+

mit · updated 2026-10-17

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

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

4-bit

Vision + text ↓ 8.2K · ♥ 31

Params

12B

Weights

≈ 6.7 GB

Mac memory

16 GB+

updated 2026-06-05

Qwen3.8-Flash-Next-Uncensored-oQ5e-mtp

from orcarouter/Qwen3.8-Flash-Next-Uncensored

5-bit

Vision + text · orcarouter ↓ 8.2K · ♥ 35

Params

180B

Weights

≈ 124 GB

Mac memory

192 GB+

qwen-community-1.0 · updated 2026-09-16

gemma-4-31b-it-4bit

from google/gemma-4-31B-it

4-bit

Vision + text · Google · Gemma ↓ 8.2K · ♥ 51

Params

31B

Weights

≈ 18.4 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-07-05

Qwen3.8-Flash-Next-4bit

from Qwen/Qwen3.8-Flash-Next

4-bit

Vision + text · Qwen ↓ 7.8K · ♥ 16

Params

177B

Weights

≈ 100 GB

Mac memory

128 GB+

updated 2026-09-02

Qwen3-VL-2B-Instruct-4bit

mlx-community/Qwen3-VL-2B-Instruct-4bit

4-bit

Vision + text ↓ 7.4K · ♥ 2

Params

2.1B

Weights

≈ 1.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-10-21

llava-v1.6-mistral-7b-4bit

mlx-community/llava-v1.6-mistral-7b-4bit

4-bit

Vision + text ↓ 7.3K · ♥ 5

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-01-11

Qwen3.5-0.8B-8bit

from Qwen/Qwen3.5-0.8B-Base

8-bit

Vision + text · Qwen ↓ 7.3K · ♥ 2

Params

853M

Weights

≈ 1.0 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-02

llava-1.5-7b-4bit

mlx-community/llava-1.5-7b-4bit

4-bit

Vision + text ↓ 7.1K · ♥ 5

Params

7.1B

Weights

≈ 4.0 GB

Mac memory

8 GB+

llama2 · updated 2024-10-11

Qwen2.5-VL-3B-Instruct-4bit

from Qwen/Qwen2.5-VL-3B-Instruct

4-bit

Vision + text · Qwen ↓ 6.5K · ♥ 8

Params

3.8B

Weights

≈ 3.1 GB

Mac memory

8 GB+

updated 2025-02-25

Qwen3-VL-8B-Instruct-4bit

mlx-community/Qwen3-VL-8B-Instruct-4bit

4-bit

Vision + text ↓ 6.4K · ♥ 11

Params

—

Weights

—

Mac memory

—

apache-2.0 · updated 2025-10-14

Qwen3.5-35B-A3B-4bit

mlx-community/Qwen3.5-35B-A3B-4bit

4-bit

Vision + text ↓ 6.3K · ♥ 48

Params

35B

Weights

≈ 20.4 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-02-24

LFM2-VL-1.6B-4bit

mlx-community/LFM2-VL-1.6B-4bit

4-bit

Vision + text ↓ 6.1K · ♥ 1

Params

1.6B

Weights

≈ 1.5 GB

Mac memory

8 GB+

lfm1.0 · updated 2025-08-16

gemma-4-26B-A4B-it-qat-4bit

mlx-community/gemma-4-26B-A4B-it-qat-4bit

4-bit

Vision + text ↓ 5.9K · ♥ 9

Params

26B

Weights

≈ 15.3 GB

Mac memory

24 GB+

updated 2026-06-05

Qwen3.8-27B-bf16

from Qwen/Qwen3.8-27B

bf16

Vision + text · Qwen ↓ 5.9K · ♥ 27

Params

27B

Weights

≈ 54.7 GB

Mac memory

64 GB+

apache-2.0 · updated 2026-11-11

Qwen3.5-122B-A10B-4bit

mlx-community/Qwen3.5-122B-A10B-4bit

4-bit

Vision + text ↓ 5.8K · ♥ 23

Params

123B

Weights

≈ 69.6 GB

Mac memory

96 GB+

apache-2.0 · updated 2026-02-24

Qwen3.6-35B-A3B-8bit

from Qwen/Qwen3.6-35B-A3B

8-bit

Vision + text · Qwen ↓ 5.6K · ♥ 37

Params

35B

Weights

≈ 37.7 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-04-16

Ornith-1.5-35B-A3B-OptiQ-4bit

from ornith-ai/Ornith-1.5-35B-A3B

4-bit

Vision + text · ornith-ai ↓ 4.9K · ♥ 4

Params

35B

Weights

≈ 20.4 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-10-30

LFM2-VL-450M-4bit

mlx-community/LFM2-VL-450M-4bit

4-bit

Vision + text ↓ 4.5K · ♥ 1

Params

451M

Weights

≈ 377 MB

Mac memory

8 GB+

lfm1.0 · updated 2025-08-16

DeepSeek-V4.1-Flash-1017-oQ2.5e-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017

Vision + text · DeepSeek ↓ 4.0K · ♥ 10

Params

102B

Weights

≈ 343 GB

Mac memory

512 GB+

mit · updated 2026-10-17

gemma-4-26b-a4b-it-8bit

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

8-bit

Vision + text · Google · Gemma ↓ 3.7K · ♥ 18

Params

26B

Weights

≈ 28.0 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-07-05

gemma-4-31b-it-8bit

from google/gemma-4-31B-it

8-bit

Vision + text · Google · Gemma ↓ 3.4K · ♥ 20

Params

31B

Weights

≈ 33.8 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-07-05

Qwen3.6-35B-A3B-5bit

from Qwen/Qwen3.6-35B-A3B

5-bit

Vision + text · Qwen ↓ 3.3K · ♥ 5

Params

35B

Weights

≈ 24.7 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-04-16

GLM-5.3-Flash-4bit

from zai-org/GLM-5.3-Flash

4-bit

Vision + text · zai-org ↓ 3.2K · ♥ 8

Params

348B

Weights

≈ 206 GB

Mac memory

256 GB+

mit · updated 2026-09-25

NVIDIA-Nemotron-3.5-Bolt-E4B-OptiQ-4bit

from nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-BF16

4-bit

Vision + text · NVIDIA ↓ 3.2K · ♥ 8

Params

7.5B

Weights

≈ 5.2 GB

Mac memory

8 GB+

openmdw-1.1 · updated 2026-10-24

Qwen3.5-27B-4bit

mlx-community/Qwen3.5-27B-4bit

4-bit

Vision + text ↓ 3.1K · ♥ 50

Params

27B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-02-24

LFM2.5-VL-1.6B-4bit

from LiquidAI/LFM2.5-1.2B-Base

4-bit

Vision + text · LiquidAI ↓ 3.1K · ♥ 4

Params

1.6B

Weights

≈ 1.5 GB

Mac memory

8 GB+

lfm1.0 · updated 2026-01-06

Qwen3.5-9B-8bit

from Qwen/Qwen3.5-9B-Base

8-bit

Vision + text · Qwen ↓ 3.0K · ♥ 21

Params

9.4B

Weights

≈ 10.4 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-02

gemma-4-E4B-it-qat-4bit

mlx-community/gemma-4-E4B-it-qat-4bit

4-bit

Vision + text ↓ 3.0K · ♥ 5

Params

7.9B

Weights

≈ 5.1 GB

Mac memory

8 GB+

updated 2026-06-05

DeepSeek-V4.1-Flash-1017-oQ4e-ngram-mtp

from deepseek-ai/DeepSeek-V4.1-Flash-1017

Vision + text · DeepSeek ↓ 3.0K · ♥ 13

Params

289B

Weights

≈ 506 GB

Mac memory

> 512 GB

mit · updated 2026-10-22

Llama-3.2-11B-Vision-Instruct-8bit

from meta-llama/Llama-3.2-11B-Vision-Instruct

8-bit

Vision + text · Meta · Llama ↓ 2.8K · ♥ 9

Params

11B

Weights

≈ 11.3 GB

Mac memory

16 GB+

llama3.2 · updated 2024-10-18

Qwen3.8-27B-mxfp4

from Qwen/Qwen3.8-27B

MXFP4

Vision + text · Qwen ↓ 2.7K · ♥ 10

Params

27B

Weights

≈ 16.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-11-11