Alkd's picture

Alkd

Alkd

·

AI & ML interests

None yet

Recent Activity

liked a model 7 days ago

opendatalab/MinerU2.5-Pro-2604-1.2B

liked a model 8 days ago

XunmeiLiu/VFIG-4B

liked a model 20 days ago

Wan-AI/Wan2.2-Animate-14B

View all activity

Organizations

None yet

liked a model 7 days ago

opendatalab/MinerU2.5-Pro-2604-1.2B

Image-Text-to-Text • 1B • Updated Apr 14 • 584k • 146

liked a model 8 days ago

XunmeiLiu/VFIG-4B

Reinforcement Learning • 4B • Updated Mar 27 • 178 • 6

liked 4 models 20 days ago

Wan-AI/Wan2.2-Animate-14B

Video-to-Video • Updated Nov 5, 2025 • 17.8k • 1.16k

black-forest-labs/FLUX.2-klein-9B

Image-to-Image • Updated Feb 24 • 136k • • 782

dx8152/Flux2-Klein-9B-Consistency

Image-to-Image • Updated Apr 19 • 39k • 403

chenxie95/X-VC

Updated Apr 22 • 47 • 3

updated a model about 1 month ago

Alkd/Qwen3-ASR-1.7B-audio8-text4-mlx

0.4B • Updated Apr 13 • 132 • 1

published a model about 1 month ago

Alkd/Qwen3-ASR-1.7B-audio8-text4-mlx

0.4B • Updated Apr 13 • 132 • 1

updated a model about 2 months ago

Alkd/Qwen3.5-4B-MLX-4bit

1.0B • Updated Apr 6 • 12

published a model about 2 months ago

Alkd/Qwen3.5-4B-MLX-4bit

1.0B • Updated Apr 6 • 12

updated a model about 2 months ago

Alkd/Qwen3-ForcedAligner-0.6B-4bit

Audio Classification • 0.4B • Updated Apr 5 • 8

published a model about 2 months ago

Alkd/Qwen3-ForcedAligner-0.6B-4bit

Audio Classification • 0.4B • Updated Apr 5 • 8

updated a model about 2 months ago

Alkd/Qwen3-ASR-1.7B-MLX-8bit

0.8B • Updated Apr 5 • 12

published a model about 2 months ago

Alkd/Qwen3-ASR-1.7B-MLX-8bit

0.8B • Updated Apr 5 • 12

updated a model about 2 months ago

Alkd/Sortformer-Diarization-CoreML

Audio Classification • Updated Apr 5 • 10 • 2

published a model about 2 months ago

Alkd/Sortformer-Diarization-CoreML

Audio Classification • Updated Apr 5 • 10 • 2

updated a model about 2 months ago

Alkd/Silero-VAD-v5-CoreML

Voice Activity Detection • Updated Apr 5 • 7

published a model about 2 months ago

Alkd/Silero-VAD-v5-CoreML

Voice Activity Detection • Updated Apr 5 • 7

New activity in mlx-community/gemma-4-e2b-4bit about 2 months ago

⚠️ Existing MLX quantized Gemma 4 models (mlx-community, unsloth) produce garbage output due to quantizing PLE (Per-Layer Embedding) layers.

#1 opened about 2 months ago by

liked a model about 2 months ago

deepseek-ai/DeepSeek-V3.2

Text Generation • 685B • Updated Dec 1, 2025 • 4.36M • • 1.44k