Apple MLX models

openthaigpt-1.0.0-7b-chat-4bit-mlx

mlx-community/openthaigpt-1.0.0-7b-chat-4bit-mlx

4-bit

Text generation ↓ 81 · ♥ 0

Params

6.8B

Weights

≈ 4.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2024-04-13

GLM-4-32B-0414-8bit

from THUDM/GLM-4-32B-0414

8-bit

Text generation · THUDM ↓ 80 · ♥ 6

Params

33B

Weights

≈ 34.6 GB

Mac memory

48 GB+

mit · updated 2025-04-22

CodelLama7B-inst-dpo-7k-mlx

mlx-community/CodelLama7B-inst-dpo-7k-mlx

Text generation ↓ 80 · ♥ 4

Params

6.7B

Weights

≈ 26.4 GB

Mac memory

32 GB+

llama2 · updated 2024-02-02

Qwen3-235B-A22B-Thinking-2507-8bit

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

8-bit

Text generation · Qwen ↓ 80 · ♥ 4

Params

235B

Weights

≈ 250 GB

Mac memory

512 GB+

apache-2.0 · updated 2025-07-25

sam3-4bit

from facebook/sam3

4-bit

Uncategorised · facebook ↓ 80 · ♥ 4

Params

860M

Weights

≈ 568 MB

Mac memory

8 GB+

updated 2026-03-28

chandra-8bit

mlx-community/chandra-8bit

8-bit

Vision + text ↓ 80 · ♥ 2

Params

—

Weights

—

Mac memory

—

openrail · updated 2025-10-21

codegemma-1.1-7b-it-8bit

from google/codegemma-1.1-7b-it

8-bit

Text generation · Google · Gemma ↓ 80 · ♥ 2

Params

8.5B

Weights

≈ 9.1 GB

Mac memory

16 GB+

gemma · updated 2025-06-02

EuroLLM-22B-Instruct-2512-mlx-8bit

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

8-bit

Text generation · utter-project ↓ 80 · ♥ 1

Params

23B

Weights

≈ 24.1 GB

Mac memory

32 GB+

apache-2.0 · updated 2025-12-16

Josiefied-Qwen2.5-14B-Instruct-abliterated-v4

from Goekdeniz-Guelmez/Josiefied-Qwen2.5-14B-Instruct-abliterated-v4

Text generation · Goekdeniz-Guelmez ↓ 80 · ♥ 1

Params

15B

Weights

≈ 29.5 GB

Mac memory

48 GB+

apache-2.0 · updated 2024-12-09

Mellum-4b-sft-python

from JetBrains/Mellum-4b-sft-python

Text generation · JetBrains ↓ 80 · ♥ 1

Params

4.0B

Weights

≈ 8.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-06-28

Qwen3-0.6B-6bit

from Qwen/Qwen3-0.6B

6-bit

Text generation · Qwen ↓ 80 · ♥ 1

Params

596M

Weights

≈ 484 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-28

Qwen3-VL-Embedding-2B-mxfp4

from Qwen/Qwen3-VL-2B-Instruct

MXFP4

Embeddings · Qwen ↓ 80 · ♥ 1

Params

2.1B

Weights

≈ 1.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-14

INTELLECT-1-Instruct-bf16

from PrimeIntellect/INTELLECT-1-Instruct

bf16

Text generation · PrimeIntellect ↓ 80 · ♥ 0

Params

10B

Weights

≈ 20.4 GB

Mac memory

32 GB+

apache-2.0 · updated 2024-11-30

LongCat-AudioDiT-3.5B-bf16

mlx-community/LongCat-AudioDiT-3.5B-bf16

bf16

Text to speech ↓ 80 · ♥ 0

Params

3.8B

Weights

≈ 15.3 GB

Mac memory

24 GB+

updated 2026-03-31

MiniCPM3-4B-4bit

from openbmb/MiniCPM3-4B

4-bit

Text generation · openbmb ↓ 80 · ♥ 0

Params

4.3B

Weights

≈ 2.4 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-03-18

Qwen2.5-14B-Instruct-1M-3bit

from Qwen/Qwen2.5-14B-Instruct-1M

3-bit

Text generation · Qwen ↓ 80 · ♥ 0

Params

15B

Weights

≈ 6.5 GB

Mac memory

16 GB+

apache-2.0 · updated 2025-01-26

Qwen3-VL-Reranker-2B-mxfp8

from Qwen/Qwen3-VL-2B-Instruct

MXFP8

Reranking · Qwen ↓ 80 · ♥ 0

Params

2.1B

Weights

≈ 2.6 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-14

agentcpm-explore-mlx-fp16

from openbmb/AgentCPM-Explore

fp16

Text generation · openbmb ↓ 80 · ♥ 0

Params

4.0B

Weights

≈ 8.0 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-01-27

bigcode-starcoder2-15b-6bit

from bigcode/starcoder2-15b

6-bit

Text generation · BigCode ↓ 80 · ♥ 0

Params

16B

Weights

≈ 13.0 GB

Mac memory

24 GB+

bigcode-openrail-m · updated 2025-02-16

gemma-4-26B-A4B-it-qat-assistant-6bit

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

6-bit

Text generation · Google · Gemma ↓ 80 · ♥ 0

Params

420M

Weights

≈ 341 MB

Mac memory

8 GB+

gemma · updated 2026-06-05

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

from google/gemma-4-26b-a4b-it

8-bit

Text generation · Google · Gemma ↓ 80 · ♥ 0

Params

25B

Weights

≈ 26.8 GB

Mac memory

32 GB+

apache-2.0 · updated 2026-05-19

karakuri-lm-8x7b-chat-v0.1-4bit

from karakuri-ai/karakuri-lm-8x7b-chat-v0.1

4-bit

Text generation · karakuri-ai ↓ 80 · ♥ 0

Params

47B

Weights

≈ 26.3 GB

Mac memory

32 GB+

apache-2.0 · updated 2024-10-11

gemma-3-27b-it-qat-8bit

from OpenGVLab/InternVL3-1B-Instruct

8-bit

Vision + text · OpenGVLab ↓ 79 · ♥ 8

Params

—

Weights

—

Mac memory

—

qwen · updated 2025-04-19

gemma-4-12B-coder-fable5-composer2.5-v1-4bit-msq

from google/gemma-4-12B-it

4-bit

Text generation · Google · Gemma ↓ 79 · ♥ 8

Params

12B

Weights

≈ 6.8 GB

Mac memory

16 GB+

apache-2.0 · updated 2026-06-18

Qwen2-VL-7B-Instruct-bf16

mlx-community/Qwen2-VL-7B-Instruct-bf16

bf16

Vision + text ↓ 79 · ♥ 4

Params

8.3B

Weights

≈ 16.6 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-03-24

GLM-4.7-REAP-50-mixed-3-4-bits

from 0xSero/GLM-4.7-185B

4-bit

Text generation · 0xSero ↓ 79 · ♥ 3

Params

185B

Weights

≈ 104 GB

Mac memory

128 GB+

apache-2.0 · updated 2026-01-04

Qwen3-Next-80B-A3B-Instruct-5bit

from Qwen/Qwen3-Next-80B-A3B-Instruct

5-bit

Text generation · Qwen ↓ 79 · ♥ 3

Params

80B

Weights

≈ 54.8 GB

Mac memory

64 GB+

apache-2.0 · updated 2025-09-13

Apriel-1.5-15b-Thinker-4bit

mlx-community/Apriel-1.5-15b-Thinker-4bit

4-bit

Text generation ↓ 79 · ♥ 2

Params

—

Weights

—

Mac memory

—

mit · updated 2025-10-03

Laguna-XS-2.1-bf16

from poolside/Laguna-XS-2.1

bf16

Text generation · poolside ↓ 79 · ♥ 2

Params

33B

Weights

≈ 66.9 GB

Mac memory

96 GB+

openmdw-1.1 · updated 2026-07-03

Ming-omni-tts-0.5B-4bit

mlx-community/Ming-omni-tts-0.5B-4bit

4-bit

Text to speech ↓ 79 · ♥ 1

Params

1.5B

Weights

≈ 834 MB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-07

Qwen3-1.7B-4bit-AWQ

from Qwen/Qwen3-1.7B

4-bit

Text generation · Qwen ↓ 79 · ♥ 1

Params

1.7B

Weights

≈ 968 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-29

3b-fr-ft-research_release-8bit

from canopylabs/orpheus-3b-0.1-pretrained

8-bit

Text to speech · canopylabs ↓ 79 · ♥ 0

Params

3.3B

Weights

≈ 3.5 GB

Mac memory

8 GB+

apache-2.0 · updated 2025-04-09

Falcon-H1-1.5B-Instruct-4bit

from tiiuae/Falcon-H1-1.5B-Instruct

4-bit

Text generation · TII · Falcon ↓ 79 · ♥ 0

Params

1.6B

Weights

≈ 875 MB

Mac memory

8 GB+

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

Huihui-GLM-4.5V-abliterated-5bit

from zai-org/GLM-4.5V

5-bit

Vision + text · zai-org ↓ 79 · ♥ 0

Params

—

Weights

—

Mac memory

—

mit · updated 2025-09-04

Qwen3-VL-Reranker-2B-6bit

from Qwen/Qwen3-VL-2B-Instruct

6-bit

Reranking · Qwen ↓ 79 · ♥ 0

Params

2.1B

Weights

≈ 2.2 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-14

chatterbox-turbo-5bit

from ResembleAI/chatterbox-turbo

5-bit

Text to speech · ResembleAI ↓ 79 · ♥ 0

Params

626M

Weights

≈ 487 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-12-17

deepseek-vl2-tiny-bf16

mlx-community/deepseek-vl2-tiny-bf16

bf16

Vision + text ↓ 79 · ♥ 0

Params

3.4B

Weights

≈ 6.7 GB

Mac memory

16 GB+

deepseek · updated 2024-12-22

whisper-base-4bit

from openai/whisper-base

4-bit

Speech recognition · OpenAI · gpt-oss ↓ 79 · ♥ 0

Params

72M

Weights

≈ 42 MB

Mac memory

8 GB+

apache-2.0 · updated 2025-12-15

DeepSeek-V3-3bit

from deepseek-ai/DeepSeek-V3

3-bit

Uncategorised · DeepSeek ↓ 78 · ♥ 3

Params

671B

Weights

≈ 294 GB

Mac memory

512 GB+

updated 2025-01-05

Magistral-Small-2506-4bit-DWQ

from mlx-community/Magistral-Small-2506-bf16

4-bit DWQ

Text generation ↓ 78 · ♥ 3

Params

24B

Weights

≈ 13.3 GB

Mac memory

24 GB+

apache-2.0 · updated 2025-06-10

Ornith-1.0-9B-OptiQ-6bit

from ornith-ai/Ornith-1.0-9B

6-bit

Vision + text · ornith-ai ↓ 78 · ♥ 3

Params

9.0B

Weights

≈ 7.3 GB

Mac memory

16 GB+

mit · updated 2026-08-07

Phi-3.5-vision-instruct-8bit

mlx-community/Phi-3.5-vision-instruct-8bit

8-bit

Text generation ↓ 78 · ♥ 3

Params

4.1B

Weights

≈ 4.4 GB

Mac memory

8 GB+

mit · updated 2025-04-19

GLM-Z1-32B-0414-4bit

from zai-org/GLM-Z1-32B-0414

4-bit

Text generation · zai-org ↓ 78 · ♥ 2

Params

33B

Weights

≈ 18.3 GB

Mac memory

24 GB+

mit · updated 2025-04-19

Hy3-oQ2e-2.31bpw

from tencent/Hy3

2-bit

Text generation · tencent ↓ 78 · ♥ 2

Params

295B

Weights

≈ 92.3 GB

Mac memory

128 GB+

apache-2.0 · updated 2026-07-15

Laguna-XS-2.1-5bit

from poolside/Laguna-XS-2.1

5-bit

Text generation · poolside ↓ 78 · ♥ 2

Params

33B

Weights

≈ 23.0 GB

Mac memory

32 GB+

openmdw-1.1 · updated 2026-07-03

Qwen1.5-1.8B-Chat-4bit

mlx-community/Qwen1.5-1.8B-Chat-4bit

4-bit

Text generation ↓ 78 · ♥ 2

Params

1.8B

Weights

≈ 1.5 GB

Mac memory

8 GB+

tongyi-qianwen-research · updated 2024-02-18

Florence-2-large-ft-8bit

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

8-bit

Vision + text ↓ 78 · ♥ 1

Params

823M

Weights

≈ 901 MB

Mac memory

8 GB+

mit · updated 2024-11-21

FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-4.5bit

from FuseAI/FuseO1-DeepSeekR1-Qwen2.5-Coder-32B-Preview

5-bit

Uncategorised · FuseAI ↓ 78 · ♥ 1

Params

33B

Weights

≈ 22.5 GB

Mac memory

32 GB+

apache-2.0 · updated 2025-02-17

Mega-ASR-bf16

from Qwen/Qwen3-ASR-1.7B

bf16

Speech recognition · Qwen ↓ 78 · ♥ 1

Params

2.0B

Weights

≈ 4.1 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-05-23

Yi-Coder-9B-Chat-8bit

mlx-community/Yi-Coder-9B-Chat-8bit

8-bit

Text generation ↓ 78 · ♥ 1

Params

8.8B

Weights

≈ 9.4 GB

Mac memory

16 GB+

apache-2.0 · updated 2024-09-05

huihui-Qwen3-VL-2B-Instruct-ab-4bit

from huihui-ai/Huihui-Qwen3-VL-2B-Instruct-abliterated

4-bit

Vision + text · huihui-ai ↓ 78 · ♥ 1

Params

2.1B

Weights

≈ 1.8 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-06-20

LongCat-AudioDiT-3.5B-8bit

mlx-community/LongCat-AudioDiT-3.5B-8bit

8-bit

Text to speech ↓ 78 · ♥ 0

Params

3.8B

Weights

≈ 4.5 GB

Mac memory

8 GB+

updated 2026-03-31

Qwen3-VL-Reranker-2B-5bit

from Qwen/Qwen3-VL-2B-Instruct

5-bit

Reranking · Qwen ↓ 78 · ♥ 0

Params

2.1B

Weights

≈ 2.0 GB

Mac memory

8 GB+

apache-2.0 · updated 2026-03-14

command-a-reasoning-08-2025-bf16

from CohereLabs/command-a-reasoning-08-2025

bf16

Text generation · Cohere ↓ 78 · ♥ 0

Params

111B

Weights

≈ 222 GB

Mac memory

256 GB+

cc-by-nc-4.0 · updated 2025-08-25

gemma-3-12b-it-6bit

from google/gemma-3-12b-pt

6-bit

Vision + text · Google · Gemma ↓ 78 · ♥ 0

Params

—

Weights

—

Mac memory

—

gemma · updated 2025-03-19

nemotron-labs-unified-asr-0.6b-4bit

from nvidia/nemotron-labs-unified-asr-0.6b

4-bit

Speech recognition · NVIDIA ↓ 78 · ♥ 0

Params

627M

Weights

≈ 472 MB

Mac memory

8 GB+

openmdw-1.1 · updated 2026-11-04

NemotronLabs-VoiceChat-11B-mlx-8bit

from nvidia/NVIDIA-NemotronLabs-VoiceChat-11B

8-bit

Uncategorised · NVIDIA ↓ 77 · ♥ 8

Params

4.3B

Weights

≈ 6.9 GB

Mac memory

16 GB+

openmdw-1.1 · updated 2026-08-05

diffusiongemma-26B-A4B-it-mxfp8

from google/diffusiongemma-26B-A4B-it

MXFP8

Vision + text · Google · Gemma ↓ 77 · ♥ 3

Params

26B

Weights

≈ 28.0 GB

Mac memory

48 GB+

apache-2.0 · updated 2026-07-15

CodeLlama-34b-Instruct-hf-4bit

mlx-community/CodeLlama-34b-Instruct-hf-4bit

4-bit

Text generation ↓ 77 · ♥ 2

Params

—

Weights

—

Mac memory

—

llama2 · updated 2024-01-30

Phi-4-mini-reasoning-bf16

from microsoft/Phi-4-mini-reasoning

bf16

Text generation · Microsoft · Phi ↓ 77 · ♥ 2

Params

3.8B

Weights

≈ 7.7 GB

Mac memory

16 GB+

mit · updated 2025-05-01