Apple MLX models

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

from Qwen/Qwen2.5-Coder-7B

4-bit

Text generation · Qwen ↓ 263K · ♥ 32

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-09-18

gpt-oss-20b-MXFP4-Q8

from openai/gpt-oss-20b

MXFP4

Text generation · OpenAI · gpt-oss ↓ 173K · ♥ 101

Params

21B

Weights

≈ 11.8 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-03-19

Kimi-K2.5

from moonshotai/Kimi-K2.5

4-bit

Text generation · Moonshot · Kimi ↓ 121K · ♥ 41

Params

1.0T

Weights

≈ 594 GB

Mac memory

> 512 GB

modified-mit · updated 2026-01-27

Qwen3-4B-Instruct-2507-4bit

from Qwen/Qwen3-4B-Instruct-2507

4-bit

Text generation · Qwen ↓ 95K · ♥ 18

Params

4.0B

Weights

≈ 2.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-01-02

Llama-3.2-1B-Instruct-4bit

from mlx-community/Llama-3.2-1B-Instruct-bf16

4-bit

Text generation ↓ 46K · ♥ 21

Params

1.2B

Weights

≈ 695 MB

Mac memory

8 GB+

llama3.2 · updated 2025-03-05

Qwen3-0.6B-4bit

from Qwen/Qwen3-0.6B

4-bit

Text generation · Qwen ↓ 44K · ♥ 18

Params

596M

Weights

≈ 335 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-0.6B-8bit

from Qwen/Qwen3-0.6B

8-bit

Text generation · Qwen ↓ 40K · ♥ 10

Params

596M

Weights

≈ 633 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-05-04

Qwen3-8B-4bit

from Qwen/Qwen3-8B

4-bit

Text generation · Qwen ↓ 33K · ♥ 20

Params

8.2B

Weights

≈ 4.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-Embedding-0.6B-4bit-DWQ

from Qwen/Qwen3-Embedding-0.6B

4-bit DWQ

Text generation · Qwen ↓ 32K · ♥ 15

Params

596M

Weights

≈ 335 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-06-06

Qwen3-4B-4bit

from Qwen/Qwen3-4B

4-bit

Text generation · Qwen ↓ 30K · ♥ 17

Params

4.0B

Weights

≈ 2.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-28

Qwen2.5-0.5B-Instruct-4bit

from Qwen/Qwen2.5-0.5B

4-bit

Text generation · Qwen ↓ 27K · ♥ 8

Params

494M

Weights

≈ 278 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-09-18

gemma-3-1b-it-qat-4bit

from google/gemma-3-1b-it

4-bit

Text generation · Google · Gemma ↓ 23K · ♥ 6

Params

1.3B

Weights

≈ 732 MB

Mac memory

8 GB+

gemma · updated 2025-04-18

Llama-3.2-3B-Instruct-4bit

from mlx-community/Llama-3.2-3B-Instruct

4-bit

Text generation ↓ 22K · ♥ 48

Params

3.2B

Weights

≈ 1.8 GB

Mac memory

8 GB+

llama3.2 · updated 2025-03-05

gemma-2-9b-it-4bit

mlx-community/gemma-2-9b-it-4bit

4-bit

Text generation ↓ 20K · ♥ 1

Params

9.2B

Weights

≈ 5.2 GB

Mac memory

8 GB+

gemma · updated 2024-11-06

Qwen3-Coder-30B-A3B-Instruct-4bit

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

4-bit

Text generation · Qwen ↓ 19K · ♥ 56

Params

31B

Weights

≈ 17.2 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-08-06

Qwen3-1.7B-4bit

from Qwen/Qwen3-1.7B

4-bit

Text generation · Qwen ↓ 16K · ♥ 7

Params

1.7B

Weights

≈ 968 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-235B-A22B-Thinking-2507-4bit

from Qwen/Qwen3-235B-A22B-Thinking-2507

4-bit

Text generation · Qwen ↓ 15K · ♥ 1

Params

235B

Weights

≈ 132 GB

Mac memory

192 GB+

apache-2.0 · updated 2025-07-25

Qwen3.8-27B-Uncensored-OptiQ-4bit

from orcarouter/Qwen3.8-27B-Uncensored

4-bit

Text generation · orcarouter ↓ 14K · ♥ 44

Params

27B

Weights

≈ 15.1 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-10-30

Qwen2.5-3B-Instruct-4bit

from Qwen/Qwen2.5-3B

4-bit

Text generation · Qwen ↓ 13K · ♥ 2

Params

3.1B

Weights

≈ 1.7 GB

Mac memory

8 GB+

qwen-research · updated 2024-09-18

Qwen2.5-7B-Instruct-4bit

from Qwen/Qwen2.5-7B

4-bit

Text generation · Qwen ↓ 13K · ♥ 17

Params

7.6B

Weights

≈ 4.3 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-11-06

Qwen2.5-1.5B-Instruct-4bit

from Qwen/Qwen2.5-1.5B

4-bit

Text generation · Qwen ↓ 11K · ♥ 5

Params

1.5B

Weights

≈ 869 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-09-18

Qwen2.5-14B-Instruct-4bit

from Qwen/Qwen2.5-14B

4-bit

Text generation · Qwen ↓ 11K · ♥ 15

Params

15B

Weights

≈ 8.3 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-09-18

SmolLM-135M-Instruct-4bit

mlx-community/SmolLM-135M-Instruct-4bit

4-bit

Text generation ↓ 8.7K · ♥ 6

Params

135M

Weights

≈ 76 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-07-16

Qwen1.5-0.5B-Chat-4bit

mlx-community/Qwen1.5-0.5B-Chat-4bit

4-bit

Text generation ↓ 8.3K · ♥ 4

Params

464M

Weights

≈ 261 MB

Mac memory

8 GB+

tongyi-qianwen-research · updated 2024-04-18

Qwen3-30B-A3B-4bit

from Qwen/Qwen3-30B-A3B

4-bit

Text generation · Qwen ↓ 7.9K · ♥ 16

Params

31B

Weights

≈ 17.2 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-04-29

Qwen3-14B-4bit

from Qwen/Qwen3-14B

4-bit

Text generation · Qwen ↓ 7.7K · ♥ 12

Params

15B

Weights

≈ 8.3 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-04-29

Qwen3.8-27B-MTP-4bit

from Qwen/Qwen3.8-27B

4-bit

Text generation · Qwen ↓ 7.3K · ♥ 46

Params

425M

Weights

≈ 239 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-11-11

gemma-3-1b-it-4bit

from google/gemma-3-1b-it

4-bit

Text generation · Google · Gemma ↓ 7.3K · ♥ 6

Params

1.3B

Weights

≈ 732 MB

Mac memory

8 GB+

gemma · updated 2025-03-12

DeepSeek-V4-Flash-2bit-DQ

mlx-community/DeepSeek-V4-Flash-2bit-DQ

2-bit

Text generation ↓ 6.8K · ♥ 56

Params

284B

Weights

≈ 89.1 GB

Mac memory

128 GB+

updated 2026-04-26

gemma-4-12b-coder-fable5-composer2.5-4bit

from yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1

4-bit

Text generation · yuxinlu1 ↓ 6.7K · ♥ 77

Params

12B

Weights

≈ 6.7 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-06-21

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

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

4-bit

Text generation · Qwen ↓ 6.6K · ♥ 16

Params

31B

Weights

≈ 17.2 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-08-06

Qwen3.5-9B-OptiQ-4bit

from Qwen/Qwen3.5-9B

4-bit

Text generation · Qwen ↓ 6.5K · ♥ 113

Params

9.0B

Weights

≈ 6.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-10-30

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

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

4-bit

Text generation · Google · Gemma ↓ 6.3K · ♥ 4

Params

25B

Weights

≈ 15.3 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-10-18

KAT-Coder-V2.5-Dev-OptiQ-4bit

from Kwaipilot/KAT-Coder-V2.5-Dev

4-bit

Text generation · Kwaipilot ↓ 6.3K · ♥ 22

Params

35B

Weights

≈ 19.5 GB

Mac memory

24 GB+

apache-2.0 · updated 2026-09-15

Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-8bit

from DavidAU/Qwen3.6-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking

8-bit

Text generation · DavidAU ↓ 6.1K · ♥ 58

Params

39B

Weights

≈ 41.5 GB

Mac memory

64 GB+

apache-2.0 · updated 2026-05-03

Llama-3.3-70B-Instruct-4bit

from meta-llama/Llama-3.3-70B-Instruct

4-bit

Text generation · Meta · Llama ↓ 6.1K · ♥ 41

Params

71B

Weights

≈ 39.7 GB

Mac memory

48 GB+

llama3.3 · updated 2024-12-06

Phi-3.5-mini-instruct-4bit

mlx-community/Phi-3.5-mini-instruct-4bit

4-bit

Text generation ↓ 5.8K · ♥ 11

Params

3.8B

Weights

≈ 2.1 GB

Mac memory

8 GB+

mit · updated 2024-08-24

Meta-Llama-3.1-8B-Instruct-4bit

mlx-community/Meta-Llama-3.1-8B-Instruct-4bit

4-bit

Text generation ↓ 5.8K · ♥ 21

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

llama3.1 · updated 2024-11-26

MiniCPM5-2B-mlx-4Bit

from openbmb/MiniCPM5-2B

4-bit

Text generation · openbmb ↓ 5.6K · ♥ 3

Params

2.5B

Weights

≈ 1.4 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-09-10

Qwen3.5-4B-OptiQ-4bit

from Qwen/Qwen3.5-4B

4-bit

Text generation · Qwen ↓ 5.5K · ♥ 38

Params

4.2B

Weights

≈ 2.4 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-10-30

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

from google/gemma-4-12B-it-qat-q4_0-unquantized

4-bit

Text generation · Google · Gemma ↓ 5.5K · ♥ 22

Params

12B

Weights

≈ 6.8 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-10-18

LFM2.5-1.2B-Instruct-4bit

from LiquidAI/LFM2.5-1.2B-Instruct

4-bit

Text generation · LiquidAI ↓ 5.5K · ♥ 3

Params

1.2B

Weights

≈ 659 MB

Mac memory

8 GB+

lfm1.0 · updated 2026-08-13

DeepSeek-R1-Distill-Qwen-32B-4bit

from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

4-bit

Text generation · DeepSeek ↓ 5.2K · ♥ 50

Params

33B

Weights

≈ 18.4 GB

Mac memory

24 GB+

updated 2025-02-26

DeepSeek-V4-Flash-4bit

mlx-community/DeepSeek-V4-Flash-4bit

4-bit

Text generation ↓ 5.1K · ♥ 33

Params

284B

Weights

≈ 160 GB

Mac memory

192 GB+

updated 2026-04-25

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

from Qwen/Qwen3-235B-A22B-Instruct-2507

4-bit

Text generation · Qwen ↓ 5.1K · ♥ 3

Params

235B

Weights

≈ 132 GB

Mac memory

192 GB+

apache-2.0 · updated 2025-07-22

Llama-3.1-8B-Instruct-4bit

from meta-llama/Llama-3.1-8B-Instruct

4-bit

Text generation · Meta · Llama ↓ 4.9K · ♥ 11

Params

8.0B

Weights

≈ 4.5 GB

Mac memory

8 GB+

llama3.1 · updated 2025-02-15

flint-mixed-3-4bit

from RecursiveSI/flint-int4

4-bit

Text generation · RecursiveSI ↓ 4.9K · ♥ 12

Params

40B

Weights

≈ 22.4 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-10-22

Qwen2.5-Coder-14B-Instruct-4bit

from Qwen/Qwen2.5-Coder-14B-Instruct

4-bit

Text generation · Qwen ↓ 4.8K · ♥ 21

Params

15B

Weights

≈ 8.3 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-11-11

Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit

mlx-community/Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-mlx-8bit

8-bit

Text generation ↓ 4.7K · ♥ 31

Params

35B

Weights

≈ 36.8 GB

Mac memory

48 GB+

updated 2026-04-23

Qwen3-235B-A22B-4bit

from Qwen/Qwen3-235B-A22B

4-bit

Text generation · Qwen ↓ 4.7K · ♥ 9

Params

235B

Weights

≈ 132 GB

Mac memory

192 GB+

apache-2.0 · updated 2025-04-29

Qwen3-Coder-Next-4bit

from Qwen/Qwen3-Coder-Next

4-bit

Text generation · Qwen ↓ 4.6K · ♥ 42

Params

80B

Weights

≈ 44.8 GB

Mac memory

64 GB+

apache-2.0 · updated 2026-02-07

GLM-5.2-mxfp4

from zai-org/GLM-5.2-FP8

MXFP4

Text generation · zai-org ↓ 4.4K · ♥ 21

Params

743B

Weights

≈ 418 GB

Mac memory

512 GB+

updated 2026-06-18

gpt-oss-120b-MXFP4-Q8

from openai/gpt-oss-120b

MXFP4

Text generation · OpenAI · gpt-oss ↓ 4.3K · ♥ 22

Params

117B

Weights

≈ 65.8 GB

Mac memory

96 GB+

apache-2.0 · updated 2025-08-30

translategemma-4b-it-4bit

from google/translategemma-4b-it

4-bit

Text generation · Google · Gemma ↓ 4.2K · ♥ 11

Params

3.9B

Weights

≈ 2.2 GB

Mac memory

8 GB+

gemma · updated 2026-01-16

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

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

4-bit

Text generation · Goekdeniz-Guelmez ↓ 4.1K · ♥ 8

Params

4.0B

Weights

≈ 2.3 GB

Mac memory

8 GB+

updated 2025-05-01

SmolLM2-135M-Instruct

from HuggingFaceTB/SmolLM2-135M-Instruct

Text generation · Hugging Face ↓ 4.1K · ♥ 0

Params

135M

Weights

≈ 269 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-10-31

Qwen2.5-Coder-1.5B-Instruct-4bit

from Qwen/Qwen2.5-Coder-1.5B

4-bit

Text generation · Qwen ↓ 4.0K · ♥ 3

Params

1.5B

Weights

≈ 869 MB

Mac memory

8 GB+

apache-2.0 · updated 2024-09-18

GLM-4.7-Flash-4bit

from zai-org/GLM-4.7-Flash

4-bit

Text generation · zai-org ↓ 3.8K · ♥ 72

Params

30B

Weights

≈ 16.9 GB

Mac memory

24 GB+

mit · updated 2026-01-25

gemma-4-E4B-it-OBLITERATED-mlx-8Bit

from OBLITERATUS/gemma-4-E4B-it-OBLITERATED

8-bit

Text generation · OBLITERATUS ↓ 3.7K · ♥ 8

Params

7.5B

Weights

≈ 8.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-05-19

Llama-3.3-70B-Instruct-8bit

from meta-llama/Llama-3.3-70B-Instruct

8-bit

Text generation · Meta · Llama ↓ 3.7K · ♥ 16

Params

71B

Weights

≈ 75.0 GB

Mac memory

96 GB+

llama3.3 · updated 2024-12-06