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 1h ago. Weights size and Mac memory are estimates from parameter count and quantisation.

Alert me about new Apple/MLX models

19 builds · clear filters

whisper-large-v3-turbo

mlx-community/whisper-large-v3-turbo
Speech recognition ↓ 345K · ♥ 122
Params
—
Weights
—
Mac memory
—

updated 2026-04-12

whisper-large-v3-mlx

mlx-community/whisper-large-v3-mlx
Speech recognition ↓ 113K · ♥ 111
Params
—
Weights
—
Mac memory
—

mit · updated 2026-04-12

whisper-large-v3-turbo-4bit

from openai/whisper-large-v3-turbo
4-bit
Speech recognition · OpenAI · gpt-oss ↓ 13K · ♥ 8
Params
807M
Weights
≈ 463 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-large-v3-turbo-8bit

from openai/whisper-large-v3-turbo
8-bit
Speech recognition · OpenAI · gpt-oss ↓ 2.2K · ♥ 4
Params
807M
Weights
≈ 864 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-large-v3-asr-fp16

mlx-community/whisper-large-v3-asr-fp16
fp16
Speech recognition ↓ 872 · ♥ 1
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-13

whisper-large-v3-4bit

from openai/whisper-large-v3
4-bit
Speech recognition · OpenAI · gpt-oss ↓ 646 · ♥ 0
Params
1.5B
Weights
≈ 877 MB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-large-v3-turbo-german-f16

from primeline/whisper-large-v3-german
Speech recognition · primeline ↓ 378 · ♥ 3
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-10-12

whisper-large-v3-turbo-fp16

from openai/whisper-large-v3-turbo
fp16
Speech recognition · OpenAI · gpt-oss ↓ 332 · ♥ 3
Params
807M
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-large-v3-fp16

from openai/whisper-large-v3
fp16
Speech recognition · OpenAI · gpt-oss ↓ 305 · ♥ 1
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

belle-whisper-large-v3-turbo-zh-8bit

mlx-community/belle-whisper-large-v3-turbo-zh-8bit
8-bit
Speech recognition ↓ 260 · ♥ 0
Params
807M
Weights
≈ 864 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

whisper-large-v3-turbo-german-f16-q4

from primeline/whisper-large-v3-german
4-bit
Speech recognition · primeline ↓ 175 · ♥ 2
Params
—
Weights
—
Mac memory
—

apache-2.0 · updated 2024-10-12

whisper-large-v3-8bit

from openai/whisper-large-v3
8-bit
Speech recognition · OpenAI · gpt-oss ↓ 171 · ♥ 0
Params
1.5B
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2025-12-15

whisper-large-v3-asr-4bit

mlx-community/whisper-large-v3-asr-4bit
4-bit
Speech recognition ↓ 74 · ♥ 0
Params
1.5B
Weights
≈ 877 MB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-13

belle-whisper-large-v3-turbo-zh-fp16

mlx-community/belle-whisper-large-v3-turbo-zh-fp16
fp16
Speech recognition ↓ 59 · ♥ 0
Params
807M
Weights
≈ 1.6 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

belle-whisper-large-v3-zh-8bit

mlx-community/belle-whisper-large-v3-zh-8bit
8-bit
Speech recognition ↓ 52 · ♥ 0
Params
1.5B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

belle-whisper-large-v3-zh-punct-fp16

mlx-community/belle-whisper-large-v3-zh-punct-fp16
fp16
Speech recognition ↓ 47 · ♥ 0
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

belle-whisper-large-v3-zh-punct-8bit

mlx-community/belle-whisper-large-v3-zh-punct-8bit
8-bit
Speech recognition ↓ 25 · ♥ 0
Params
1.5B
Weights
≈ 1.7 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

belle-whisper-large-v3-zh-fp16

mlx-community/belle-whisper-large-v3-zh-fp16
fp16
Speech recognition ↓ 21 · ♥ 0
Params
1.5B
Weights
≈ 3.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-05-30

whisper-large-v3-asr-5bit

mlx-community/whisper-large-v3-asr-5bit
5-bit
Speech recognition ↓ 13 · ♥ 0
Params
1.5B
Weights
≈ 1.1 GB
Mac memory
8 GB+

apache-2.0 · updated 2026-01-13