1 10

Alkd

AI & ML interests

None yet

Recent Activity

updated a model about 5 hours ago

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

published a model about 5 hours ago

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

updated a model about 5 hours ago

Alkd/Qwen3-ForcedAligner-0.6B-4bit

View all activity

Organizations

None yet

updated a model about 5 hours ago

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

1.0B • Updated about 5 hours ago

published a model about 5 hours ago

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

1.0B • Updated about 5 hours ago

updated a model about 5 hours ago

Alkd/Qwen3-ForcedAligner-0.6B-4bit

Audio Classification • Updated about 5 hours ago

published a model about 5 hours ago

Alkd/Qwen3-ForcedAligner-0.6B-4bit

Audio Classification • Updated about 5 hours ago

updated a model about 5 hours ago

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

0.8B • Updated about 5 hours ago

published a model about 5 hours ago

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

0.8B • Updated about 5 hours ago

updated a model about 5 hours ago

Alkd/Sortformer-Diarization-CoreML

Audio Classification • Updated about 5 hours ago

published a model about 5 hours ago

Alkd/Sortformer-Diarization-CoreML

Audio Classification • Updated about 5 hours ago

updated a model about 5 hours ago

Alkd/Silero-VAD-v5-CoreML

Voice Activity Detection • Updated about 5 hours ago

published a model about 5 hours ago

Alkd/Silero-VAD-v5-CoreML

Voice Activity Detection • Updated about 5 hours ago

New activity in mlx-community/gemma-4-e2b-4bit 1 day ago

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

#1 opened 1 day ago by

Alkd

liked a model 1 day ago

deepseek-ai/DeepSeek-V3.2

Text Generation • 685B • Updated Dec 1, 2025 • 964k • 1.37k

liked a Space 2 days ago

Qwen3.5 WebGPU

😻

Run Qwen3.5 (0.8B, 2B, 4B) in-browser with Transformers.js

liked a Space 4 days ago

Qwen3.5 Omni Offline Demo

🌍

101

Chat with a multimodal AI using text, images, audio, or video

liked a dataset 10 days ago

CAiRE/ASCEND

Viewer • Updated Jul 16, 2024 • 12.3k • 798 • 47

liked a model 10 days ago

MediaTek-Research/BreezyVoice

Updated Feb 18, 2025 • 52

updated a model 11 days ago

Alkd/sumi-qwen3.5-4b-mlx

Updated 11 days ago

updated a dataset 11 days ago

Alkd/asr-postprocessor-data

Viewer • Updated 11 days ago • 2.9k • 92

liked a model 13 days ago

Qwen/Qwen3-Omni-30B-A3B-Instruct

Any-to-Any • 35B • Updated Sep 22, 2025 • 349k • 896

published a model 13 days ago

Alkd/sumi-qwen3.5-4b-mlx

Updated 11 days ago

Alkd

AI & ML interests

Recent Activity

Organizations

Alkd's activity

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

Qwen3.5 WebGPU

Qwen3.5 Omni Offline Demo