UEmbed multimodal embedding models running dense text embeddings on Apple Silicon via MLX.
Volodymyr IERMOLAIEV PRO
majentik
AI & ML interests
Bleeding-edge AI models and most prominent ML open-source projects.
Recent Activity
updated a dataset about 17 hours ago
majentik/garden-quant-bench updated a model 1 day ago
majentik/MERaLiON-3-10B-MLX updated a model 1 day ago
majentik/TinyLlama-1.1B-Chat-v1.0-QuadRotor-Full-4bitOrganizations
Qwen3-Embedding model packs in ONNX, GGUF, and MLX formats for retrieval and embedding workloads.
-
majentik/Qwen3-Embedding-0.6B-GGUF-IQ4_XS
Feature Extraction • 0.6B • Updated • 58 • 1 -
majentik/Qwen3-Embedding-0.6B-GGUF-Q4_K_M
Feature Extraction • 0.6B • Updated • 83 -
majentik/Qwen3-Embedding-0.6B-GGUF-Q5_K_M
Feature Extraction • 0.6B • Updated • 40 -
majentik/Qwen3-Embedding-0.6B-GGUF-Q8_0
Feature Extraction • 0.6B • Updated • 68
Session-verified MLX packs that passed a smoke gate against a reference implementation before publication.
-
majentik/MERaLiON-3-10B-MLX-8bit
Automatic Speech Recognition • 3B • Updated • 14 -
majentik/MERaLiON-3-10B-MLX-4bit
Automatic Speech Recognition • 2B • Updated • 17 -
majentik/MERaLiON-3-3B-ASR-MLX-8bit
Automatic Speech Recognition • 1B • Updated • 31 -
majentik/MOSS-Transcribe-Diarize-MLX-8bit
Automatic Speech Recognition • 0.5B • Updated • 169 • 1
OCR and document-understanding MLX packs, including Unlimited-OCR and the GELab-Zero preview family.
-
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-4bit
Image-Text-to-Text • 1B • Updated • 17 -
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit
Image-Text-to-Text • 1B • Updated • 8 -
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-8bit
Image-Text-to-Text • 2B • Updated • 5 -
majentik/Unlimited-OCR-MLX-6bit
Image-Text-to-Text • 1B • Updated • 122
MERaLiON speech and ASR model packs (MLX, GGUF, quantized variants) for Apple Silicon.
-
majentik/MERaLiON-2-10B-MLX
Automatic Speech Recognition • Updated • 6 -
majentik/MERaLiON-2-10B-MLX-4bit
Automatic Speech Recognition • Updated • 9 -
majentik/MERaLiON-2-10B-RotorQuant-MLX-2bit
Automatic Speech Recognition • Updated • 37 -
majentik/MERaLiON-2-10B-RotorQuant-MLX-4bit
Automatic Speech Recognition • Updated • 47
Quantized GGUF, MLX, and FP8/FP4 packs of the Qwen 3.6 model family.
Agentic 30B vision-language model from Meta, quantized for Apple Silicon with MLX.
Quantized GGUF and MLX packs of the Nemotron 3 model family (Nano, Nano-Omni, Super).
-
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-IQ4_XS
Text Generation • 32B • Updated • 30 -
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q2_K
Text Generation • 32B • Updated • 39 -
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q3_K_M
Text Generation • 32B • Updated • 30 -
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q4_K_M
Text Generation • 32B • Updated • 37
The verified, rebuilt gpt-oss-20b RotorQuant GGUF quant family (the retired 120b tombstones are excluded).
-
majentik/gpt-oss-20b-RotorQuant-GGUF-IQ4_XS
Text Generation • 21B • Updated • 167 -
majentik/gpt-oss-20b-RotorQuant-GGUF-Q2_K
Text Generation • 21B • Updated • 136 -
majentik/gpt-oss-20b-RotorQuant-GGUF-Q3_K_M
Text Generation • 21B • Updated • 119 -
majentik/gpt-oss-20b-RotorQuant-GGUF-Q4_K_M
Text Generation • 21B • Updated • 175
Automatic speech recognition and transcription/diarization MLX packs that run natively on Apple Silicon.
-
majentik/cohere-transcribe-arabic-07-2026-MLX-4bit
Automatic Speech Recognition • 0.5B • Updated • 47 -
majentik/cohere-transcribe-arabic-07-2026-MLX-6bit
Automatic Speech Recognition • 0.6B • Updated • 44 -
majentik/cohere-transcribe-arabic-07-2026-MLX-8bit
Automatic Speech Recognition • 0.8B • Updated • 98 -
majentik/MERaLiON-3-3B-ASR-MLX-8bit
Automatic Speech Recognition • 1B • Updated • 31
Quantized GGUF and MLX packs of the Qwen 3.5 model family, including the 397B-A17B MoE.
-
majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS
Text Generation • 27B • Updated • 36 -
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q2_K
Text Generation • 27B • Updated • 63 • 2 -
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q3_K_M
Text Generation • 27B • Updated • 64 -
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q4_K_M
Text Generation • 27B • Updated • 40
Quantized GGUF and MLX packs of the Gemma 4 family (dense and MoE variants) for local inference.
-
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-IQ4_XS
Image-Text-to-Text • 25B • Updated • 243 -
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q2_K
Image-Text-to-Text • 25B • Updated • 211 -
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q3_K_M
Image-Text-to-Text • 25B • Updated • 194 -
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q4_K_M
Image-Text-to-Text • 25B • Updated • 522 • 1
UEmbed multimodal embedding models running dense text embeddings on Apple Silicon via MLX.
Agentic 30B vision-language model from Meta, quantized for Apple Silicon with MLX.
Qwen3-Embedding model packs in ONNX, GGUF, and MLX formats for retrieval and embedding workloads.
-
majentik/Qwen3-Embedding-0.6B-GGUF-IQ4_XS
Feature Extraction • 0.6B • Updated • 58 • 1 -
majentik/Qwen3-Embedding-0.6B-GGUF-Q4_K_M
Feature Extraction • 0.6B • Updated • 83 -
majentik/Qwen3-Embedding-0.6B-GGUF-Q5_K_M
Feature Extraction • 0.6B • Updated • 40 -
majentik/Qwen3-Embedding-0.6B-GGUF-Q8_0
Feature Extraction • 0.6B • Updated • 68
Quantized GGUF and MLX packs of the Nemotron 3 model family (Nano, Nano-Omni, Super).
-
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-IQ4_XS
Text Generation • 32B • Updated • 30 -
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q2_K
Text Generation • 32B • Updated • 39 -
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q3_K_M
Text Generation • 32B • Updated • 30 -
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q4_K_M
Text Generation • 32B • Updated • 37
Session-verified MLX packs that passed a smoke gate against a reference implementation before publication.
-
majentik/MERaLiON-3-10B-MLX-8bit
Automatic Speech Recognition • 3B • Updated • 14 -
majentik/MERaLiON-3-10B-MLX-4bit
Automatic Speech Recognition • 2B • Updated • 17 -
majentik/MERaLiON-3-3B-ASR-MLX-8bit
Automatic Speech Recognition • 1B • Updated • 31 -
majentik/MOSS-Transcribe-Diarize-MLX-8bit
Automatic Speech Recognition • 0.5B • Updated • 169 • 1
The verified, rebuilt gpt-oss-20b RotorQuant GGUF quant family (the retired 120b tombstones are excluded).
-
majentik/gpt-oss-20b-RotorQuant-GGUF-IQ4_XS
Text Generation • 21B • Updated • 167 -
majentik/gpt-oss-20b-RotorQuant-GGUF-Q2_K
Text Generation • 21B • Updated • 136 -
majentik/gpt-oss-20b-RotorQuant-GGUF-Q3_K_M
Text Generation • 21B • Updated • 119 -
majentik/gpt-oss-20b-RotorQuant-GGUF-Q4_K_M
Text Generation • 21B • Updated • 175
OCR and document-understanding MLX packs, including Unlimited-OCR and the GELab-Zero preview family.
-
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-4bit
Image-Text-to-Text • 1B • Updated • 17 -
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit
Image-Text-to-Text • 1B • Updated • 8 -
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-8bit
Image-Text-to-Text • 2B • Updated • 5 -
majentik/Unlimited-OCR-MLX-6bit
Image-Text-to-Text • 1B • Updated • 122
Automatic speech recognition and transcription/diarization MLX packs that run natively on Apple Silicon.
-
majentik/cohere-transcribe-arabic-07-2026-MLX-4bit
Automatic Speech Recognition • 0.5B • Updated • 47 -
majentik/cohere-transcribe-arabic-07-2026-MLX-6bit
Automatic Speech Recognition • 0.6B • Updated • 44 -
majentik/cohere-transcribe-arabic-07-2026-MLX-8bit
Automatic Speech Recognition • 0.8B • Updated • 98 -
majentik/MERaLiON-3-3B-ASR-MLX-8bit
Automatic Speech Recognition • 1B • Updated • 31
MERaLiON speech and ASR model packs (MLX, GGUF, quantized variants) for Apple Silicon.
-
majentik/MERaLiON-2-10B-MLX
Automatic Speech Recognition • Updated • 6 -
majentik/MERaLiON-2-10B-MLX-4bit
Automatic Speech Recognition • Updated • 9 -
majentik/MERaLiON-2-10B-RotorQuant-MLX-2bit
Automatic Speech Recognition • Updated • 37 -
majentik/MERaLiON-2-10B-RotorQuant-MLX-4bit
Automatic Speech Recognition • Updated • 47
Quantized GGUF and MLX packs of the Qwen 3.5 model family, including the 397B-A17B MoE.
-
majentik/Qwen3.5-27B-RotorQuant-GGUF-IQ4_XS
Text Generation • 27B • Updated • 36 -
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q2_K
Text Generation • 27B • Updated • 63 • 2 -
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q3_K_M
Text Generation • 27B • Updated • 64 -
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q4_K_M
Text Generation • 27B • Updated • 40
Quantized GGUF, MLX, and FP8/FP4 packs of the Qwen 3.6 model family.
Quantized GGUF and MLX packs of the Gemma 4 family (dense and MoE variants) for local inference.
-
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-IQ4_XS
Image-Text-to-Text • 25B • Updated • 243 -
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q2_K
Image-Text-to-Text • 25B • Updated • 211 -
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q3_K_M
Image-Text-to-Text • 25B • Updated • 194 -
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q4_K_M
Image-Text-to-Text • 25B • Updated • 522 • 1