Skip to content
AI Model Radar
Apple silicon

Apple MLX models

5,841 models converted for Apple MLX, listed from Hugging Face’s mlx-community, refreshed 43m ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

43 builds · clear filters

Qwen3-Embedding-0.6B-8bit

from Qwen/Qwen3-Embedding-0.6B
8-bit
Embeddings · Qwen ↓ 6.7K · ♥ 2
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-07-14

embeddinggemma-2-8bit

from google/embeddinggemma-2
8-bit
Embeddings · Google · Gemma ↓ 5.8K · ♥ 9
Params
744M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

embeddinggemma-2-bf16

from google/embeddinggemma-2
bf16
Embeddings · Google · Gemma ↓ 5.6K · ♥ 11
Params
744M
Weights
≈ 1.5 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

Qwen3-Embedding-4B-4bit-DWQ

from Qwen/Qwen3-Embedding-4B
4-bit DWQ
Embeddings · Qwen ↓ 4.7K · ♥ 19
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-07

bge-m3-mlx-fp16

from BAAI/bge-m3
fp16
Embeddings · BAAI ↓ 3.2K · ♥ 4
Params
568M
Weights
≈ 1.1 GB
Mac memory
8 GB+

mit · updated 2026-03-16

Qwen3-Embedding-8B-4bit-DWQ

from Qwen/Qwen3-Embedding-8B
4-bit DWQ
Embeddings · Qwen ↓ 2.5K · ♥ 11
Params
7.6B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-06-23

bge-m3-mlx-8bit

from BAAI/bge-m3
8-bit
Embeddings · BAAI ↓ 1.8K · ♥ 2
Params
568M
Weights
≈ 604 MB
Mac memory
8 GB+

mit · updated 2026-03-16

Qwen3-Embedding-8B-mxfp8

from Qwen/Qwen3-8B-Base
MXFP8
Embeddings · Qwen ↓ 1.0K · ♥ 4
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-02-11

Qwen3-VL-Embedding-2B-8bit

from Qwen/Qwen3-VL-2B-Instruct
8-bit
Embeddings · Qwen ↓ 930 · ♥ 0
Params
2.1B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-13

embeddinggemma-2-4bit

from google/embeddinggemma-2
4-bit
Embeddings · Google · Gemma ↓ 925 · ♥ 4
Params
744M
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

bge-small-en-v1.5-bf16

mlx-community/bge-small-en-v1.5-bf16
bf16
Embeddings ↓ 860 · ♥ 2
Params
33M
Weights
≈ 67 MB
Mac memory
8 GB+

mit · updated 2025-04-02

Qwen3-Embedding-4B-mxfp8

from Qwen/Qwen3-4B-Base
MXFP8
Embeddings · Qwen ↓ 854 · ♥ 2
Params
4.0B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-11

Qwen3-Embedding-0.6B-mxfp8

from Qwen/Qwen3-0.6B-Base
MXFP8
Embeddings · Qwen ↓ 750 · ♥ 3
Params
596M
Weights
≈ 633 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-02-11

embeddinggemma-2-mxfp8

from google/embeddinggemma-2
MXFP8
Embeddings · Google · Gemma ↓ 717 · ♥ 5
Params
744M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

CLM-v0.1-8B-MLX-8bit

from Qwen/Qwen3-8B
8-bit
Embeddings · Qwen ↓ 635 · ♥ 9
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-09-29

bge-m3-mlx-4bit

from BAAI/bge-m3
4-bit
Embeddings · BAAI ↓ 569 · ♥ 1
Params
568M
Weights
≈ 320 MB
Mac memory
8 GB+

mit · updated 2026-03-16

bge-small-en-v1.5-8bit

mlx-community/bge-small-en-v1.5-8bit
8-bit
Embeddings ↓ 498 · ♥ 1
Params
33M
Weights
≈ 36 MB
Mac memory
8 GB+

mit · updated 2025-04-02

embeddinggemma-2-5bit

from google/embeddinggemma-2
5-bit
Embeddings · Google · Gemma ↓ 354 · ♥ 3
Params
744M
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

embeddinggemma-2-mxfp4

from google/embeddinggemma-2
MXFP4
Embeddings · Google · Gemma ↓ 350 · ♥ 3
Params
744M
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

Qwen3-VL-Embedding-2B-4bit

from Qwen/Qwen3-VL-2B-Instruct
4-bit
Embeddings · Qwen ↓ 338 · ♥ 2
Params
2.1B
Weights
≈ 1.8 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-13

embeddinggemma-2-nvfp4

from google/embeddinggemma-2
4-bit
Embeddings · Google · Gemma ↓ 325 · ♥ 2
Params
744M
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

embeddinggemma-2-6bit

from google/embeddinggemma-2
6-bit
Embeddings · Google · Gemma ↓ 321 · ♥ 3
Params
744M
Weights
≈ 1.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-10-06

MOSS-Audio-Tokenizer-Nano

from OpenMOSS-Team/MOSS-Audio-Tokenizer
Embeddings · OpenMOSS-Team ↓ 297 · ♥ 0
Params
22M
Weights
≈ 44 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-04-24

multilingual-e5-large-mlx

mlx-community/multilingual-e5-large-mlx
Embeddings ↓ 278 · ♥ 5
Params
—
Weights
—
Mac memory
—

mit · updated 2024-01-11

e5-mistral-7b-instruct-mlx

mlx-community/e5-mistral-7b-instruct-mlx
Embeddings ↓ 210 · ♥ 10
Params
—
Weights
—
Mac memory
—

mit · updated 2024-01-05

bge-small-en-v1.5-4bit

mlx-community/bge-small-en-v1.5-4bit
4-bit
Embeddings ↓ 198 · ♥ 1
Params
33M
Weights
≈ 19 MB
Mac memory
8 GB+

mit · updated 2025-04-02

mxbai-embed-large-v1

from mixedbread-ai/mxbai-embed-large-v1
Embeddings · mixedbread-ai ↓ 168 · ♥ 4
Params
335M
Weights
≈ 670 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-07-23

bge-m3-mlx-6bit

from BAAI/bge-m3
6-bit
Embeddings · BAAI ↓ 159 · ♥ 0
Params
568M
Weights
≈ 462 MB
Mac memory
8 GB+

mit · updated 2026-03-16

multilingual-e5-large

mlx-community/multilingual-e5-large
Embeddings ↓ 139 · ♥ 1
Params
560M
Weights
≈ 1.1 GB
Mac memory
8 GB+

mit · updated 2025-07-30

Qwen3-VL-Embedding-2B-bf16

from Qwen/Qwen3-VL-2B-Instruct
bf16
Embeddings · Qwen ↓ 130 · ♥ 0
Params
2.1B
Weights
≈ 4.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-13

bge-small-en-v1.5-6bit

mlx-community/bge-small-en-v1.5-6bit
6-bit
Embeddings ↓ 127 · ♥ 0
Params
33M
Weights
≈ 27 MB
Mac memory
8 GB+

mit · updated 2025-04-02

CLM-v0.1-8B-MLX-4bit

from Qwen/Qwen3-8B
4-bit
Embeddings · Qwen ↓ 104 · ♥ 1
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-09-29

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

Qwen3-VL-Embedding-2B-mxfp8

from Qwen/Qwen3-VL-2B-Instruct
MXFP8
Embeddings · Qwen ↓ 71 · ♥ 1
Params
2.1B
Weights
≈ 2.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-14

Qwen3-VL-Embedding-2B-6bit

from Qwen/Qwen3-VL-2B-Instruct
6-bit
Embeddings · Qwen ↓ 64 · ♥ 0
Params
2.1B
Weights
≈ 2.2 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-13

Octen-Embedding-4B-MLX-4bit

from Octen/Octen-Embedding-4B
4-bit
Embeddings · Octen ↓ 60 · ♥ 1
Params
4.0B
Weights
≈ 2.3 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-08-24

wespeaker-voxceleb-resnet34-LM

from pyannote/wespeaker-voxceleb-resnet34-LM
Embeddings · pyannote ↓ 47 · ♥ 3
Params
—
Weights
—
Mac memory
—

mit · updated 2026-01-16

CLM-v0.1-8B-MLX-5bit

from Qwen/Qwen3-8B
5-bit
Embeddings · Qwen ↓ 46 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-09-29

Qwen3-VL-Embedding-2B-5bit

from Qwen/Qwen3-VL-2B-Instruct
5-bit
Embeddings · Qwen ↓ 33 · ♥ 0
Params
2.1B
Weights
≈ 2.0 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-03-13

Qwen3-VL-Embedding-2B-nvfp4

from Qwen/Qwen3-VL-2B-Instruct
Embeddings · Qwen ↓ 30 · ♥ 0
Params
2.1B
Weights
≈ 7.7 GB
Mac memory
16 GB+

apache-2.0 · updated 2026-03-13

nemo-nano-codec-22khz-1.89kbps-21.5fps

from nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps
Embeddings · NVIDIA ↓ 0 · ♥ 1
Params
105M
Weights
≈ 419 MB
Mac memory
8 GB+

nvidia-open-model-license · updated 2026-07-10

MOSS-Audio-Tokenizer-MLX-8bit

from OpenMOSS-Team/MOSS-Audio-Tokenizer
8-bit
Embeddings · OpenMOSS-Team ↓ 0 · ♥ 0
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2026-04-11

mimi-encoder-mlx

from kyutai/mimi
Embeddings · kyutai ↓ 0 · ♥ 0
Params
—
Weights
—
Mac memory
—

cc-by-4.0 · updated 2026-06-10