🤝 Open to Collab

Volodymyr IERMOLAIEV PRO

majentik

10 3 3

riller-hf's profile picture

BlueishDragonz's profile picture

Datatypes's profile picture

https://www.ajentik.ai

yamyr
vyanok

AI & ML interests

Bleeding-edge AI models and most prominent ML open-source projects.

Recent Activity

updated a dataset 17 days ago

majentik/SASRBench-v1

published a dataset 17 days ago

majentik/SASRBench-v1

updated a dataset 17 days ago

majentik/WildASR

View all activity

Organizations

majentik 's collections 12

UEmbed — multimodal embeddings (MLX, dense text)

UEmbed multimodal embedding models running dense text embeddings on Apple Silicon via MLX.

majentik/UEmbed-2B-MLX-8bit

Feature Extraction • 2B • Updated Aug 10 • 10
majentik/UEmbed-2B-MLX-4bit

Feature Extraction • 2B • Updated Aug 10 • 13
majentik/UEmbed-4B-MLX-8bit

Feature Extraction • 4B • Updated Aug 11 • 15
majentik/UEmbed-4B-MLX-4bit

Feature Extraction • 4B • Updated Aug 11 • 39

Embeddings (ONNX)

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 Jul 20 • 31 • 1
majentik/Qwen3-Embedding-0.6B-GGUF-Q4_K_M

Feature Extraction • 0.6B • Updated Jul 20 • 121
majentik/Qwen3-Embedding-0.6B-GGUF-Q5_K_M

Feature Extraction • 0.6B • Updated Jul 20 • 69
majentik/Qwen3-Embedding-0.6B-GGUF-Q8_0

Feature Extraction • 0.6B • Updated Jul 20 • 57

Verified MLX releases (smoke-gated)

Session-verified MLX packs that passed a smoke gate against a reference implementation before publication.

majentik/MERaLiON-3-10B-MLX-8bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 12
majentik/MERaLiON-3-10B-MLX-4bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 9
majentik/MERaLiON-3-3B-ASR-MLX-8bit

Automatic Speech Recognition • 3B • Updated 20 days ago • 33
majentik/MOSS-Transcribe-Diarize-MLX-8bit

Automatic Speech Recognition • 0.9B • Updated Aug 2 • 91 • 1

OCR & Document AI (MLX)

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 • 4B • Updated Jul 14 • 4
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit

Image-Text-to-Text • 4B • Updated Jul 14 • 4
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-8bit

Image-Text-to-Text • 4B • Updated Jul 14 • 2
majentik/Unlimited-OCR-MLX-6bit

Image-Text-to-Text • 3B • Updated Jul 20 • 28

MERaLiON — Singapore speech models on MLX

MERaLiON speech and ASR model packs (MLX, GGUF, quantized variants) for Apple Silicon.

majentik/MERaLiON-3-10B-MLX

Automatic Speech Recognition • Updated 20 days ago • 109
majentik/MERaLiON-3-10B-MLX-4bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 9
majentik/MERaLiON-3-10B-MLX-8bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 12
majentik/MERaLiON-3-10B-RotorQuant-MLX-2bit

Automatic Speech Recognition • Updated Jul 20 • 18

Qwen 3.6 — quantized

Quantized GGUF, MLX, and FP8/FP4 packs of the Qwen 3.6 model family.

majentik/Qwen3.6-27B-MLX-2bit

Image-Text-to-Text • 28B • Updated Aug 10 • 104
majentik/Qwen3.6-27B-MLX-3bit

Image-Text-to-Text • 28B • Updated Aug 10 • 148 • 1
majentik/Qwen3.6-27B-MLX-4bit

Image-Text-to-Text • 28B • Updated Aug 10 • 55
majentik/Qwen3.6-27B-MLX-5bit

Image-Text-to-Text • 28B • Updated Aug 10 • 27

Meta Muse Glimmer — MLX

Agentic 30B vision-language model from Meta, quantized for Apple Silicon with MLX.

majentik/Muse-Glimmer-30B-MLX-8bit

Image-Text-to-Text • 30B • Updated 27 days ago • 366
majentik/Muse-Glimmer-30B-MLX-6bit

Image-Text-to-Text • 30B • Updated 27 days ago • 214
majentik/Muse-Glimmer-30B-MLX-4bit

Image-Text-to-Text • 30B • Updated 27 days ago • 273

Nemotron — quantized

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 Jul 20 • 46
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q2_K

Text Generation • 32B • Updated Jul 20 • 23
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q3_K_M

Text Generation • 32B • Updated Jul 20 • 26
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q5_K_M

Text Generation • 32B • Updated Jul 20 • 32

gpt-oss — rebuilt GGUFs

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 22 days ago • 119
majentik/gpt-oss-20b-RotorQuant-GGUF-Q2_K

Text Generation • 21B • Updated 22 days ago • 123
majentik/gpt-oss-20b-RotorQuant-GGUF-Q3_K_M

Text Generation • 21B • Updated 22 days ago • 86
majentik/gpt-oss-20b-RotorQuant-GGUF-Q4_K_M

Text Generation • 21B • Updated 22 days ago • 135

ASR on Apple Silicon (MLX)

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 • 2B • Updated Aug 10 • 38
majentik/cohere-transcribe-arabic-07-2026-MLX-6bit

Automatic Speech Recognition • 2B • Updated Aug 10 • 27
majentik/cohere-transcribe-arabic-07-2026-MLX-8bit

Automatic Speech Recognition • 2B • Updated Aug 10 • 120
majentik/MERaLiON-3-3B-ASR-MLX-8bit

Automatic Speech Recognition • 3B • Updated 20 days ago • 33

Qwen 3.5 — quantized

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 22 days ago • 111
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q2_K

Text Generation • 27B • Updated 22 days ago • 117 • 2
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q3_K_M

Text Generation • 27B • Updated 22 days ago • 102
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q4_K_M

Text Generation • 27B • Updated 22 days ago • 114

Gemma 4 — quantized (GGUF + MLX)

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 Jul 20 • 68
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q2_K

Image-Text-to-Text • 25B • Updated Jul 20 • 399
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q3_K_M

Image-Text-to-Text • 25B • Updated Jul 20 • 84
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q4_K_M

Image-Text-to-Text • 25B • Updated Jul 20 • 257 • 1

UEmbed — multimodal embeddings (MLX, dense text)

UEmbed multimodal embedding models running dense text embeddings on Apple Silicon via MLX.

majentik/UEmbed-2B-MLX-8bit

Feature Extraction • 2B • Updated Aug 10 • 10
majentik/UEmbed-2B-MLX-4bit

Feature Extraction • 2B • Updated Aug 10 • 13
majentik/UEmbed-4B-MLX-8bit

Feature Extraction • 4B • Updated Aug 11 • 15
majentik/UEmbed-4B-MLX-4bit

Feature Extraction • 4B • Updated Aug 11 • 39

Meta Muse Glimmer — MLX

Agentic 30B vision-language model from Meta, quantized for Apple Silicon with MLX.

majentik/Muse-Glimmer-30B-MLX-8bit

Image-Text-to-Text • 30B • Updated 27 days ago • 366
majentik/Muse-Glimmer-30B-MLX-6bit

Image-Text-to-Text • 30B • Updated 27 days ago • 214
majentik/Muse-Glimmer-30B-MLX-4bit

Image-Text-to-Text • 30B • Updated 27 days ago • 273

Embeddings (ONNX)

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 Jul 20 • 31 • 1
majentik/Qwen3-Embedding-0.6B-GGUF-Q4_K_M

Feature Extraction • 0.6B • Updated Jul 20 • 121
majentik/Qwen3-Embedding-0.6B-GGUF-Q5_K_M

Feature Extraction • 0.6B • Updated Jul 20 • 69
majentik/Qwen3-Embedding-0.6B-GGUF-Q8_0

Feature Extraction • 0.6B • Updated Jul 20 • 57

Nemotron — quantized

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 Jul 20 • 46
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q2_K

Text Generation • 32B • Updated Jul 20 • 23
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q3_K_M

Text Generation • 32B • Updated Jul 20 • 26
majentik/Nemotron-3-Nano-30B-A3B-RotorQuant-GGUF-Q5_K_M

Text Generation • 32B • Updated Jul 20 • 32

Verified MLX releases (smoke-gated)

Session-verified MLX packs that passed a smoke gate against a reference implementation before publication.

majentik/MERaLiON-3-10B-MLX-8bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 12
majentik/MERaLiON-3-10B-MLX-4bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 9
majentik/MERaLiON-3-3B-ASR-MLX-8bit

Automatic Speech Recognition • 3B • Updated 20 days ago • 33
majentik/MOSS-Transcribe-Diarize-MLX-8bit

Automatic Speech Recognition • 0.9B • Updated Aug 2 • 91 • 1

gpt-oss — rebuilt GGUFs

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 22 days ago • 119
majentik/gpt-oss-20b-RotorQuant-GGUF-Q2_K

Text Generation • 21B • Updated 22 days ago • 123
majentik/gpt-oss-20b-RotorQuant-GGUF-Q3_K_M

Text Generation • 21B • Updated 22 days ago • 86
majentik/gpt-oss-20b-RotorQuant-GGUF-Q4_K_M

Text Generation • 21B • Updated 22 days ago • 135

OCR & Document AI (MLX)

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 • 4B • Updated Jul 14 • 4
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-6bit

Image-Text-to-Text • 4B • Updated Jul 14 • 4
majentik/GELab-Zero-4B-preview-Sico-Evolution-MLX-8bit

Image-Text-to-Text • 4B • Updated Jul 14 • 2
majentik/Unlimited-OCR-MLX-6bit

Image-Text-to-Text • 3B • Updated Jul 20 • 28

ASR on Apple Silicon (MLX)

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 • 2B • Updated Aug 10 • 38
majentik/cohere-transcribe-arabic-07-2026-MLX-6bit

Automatic Speech Recognition • 2B • Updated Aug 10 • 27
majentik/cohere-transcribe-arabic-07-2026-MLX-8bit

Automatic Speech Recognition • 2B • Updated Aug 10 • 120
majentik/MERaLiON-3-3B-ASR-MLX-8bit

Automatic Speech Recognition • 3B • Updated 20 days ago • 33

MERaLiON — Singapore speech models on MLX

MERaLiON speech and ASR model packs (MLX, GGUF, quantized variants) for Apple Silicon.

majentik/MERaLiON-3-10B-MLX

Automatic Speech Recognition • Updated 20 days ago • 109
majentik/MERaLiON-3-10B-MLX-4bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 9
majentik/MERaLiON-3-10B-MLX-8bit

Automatic Speech Recognition • 10B • Updated Jul 7 • 12
majentik/MERaLiON-3-10B-RotorQuant-MLX-2bit

Automatic Speech Recognition • Updated Jul 20 • 18

Qwen 3.5 — quantized

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 22 days ago • 111
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q2_K

Text Generation • 27B • Updated 22 days ago • 117 • 2
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q3_K_M

Text Generation • 27B • Updated 22 days ago • 102
majentik/Qwen3.5-27B-RotorQuant-GGUF-Q4_K_M

Text Generation • 27B • Updated 22 days ago • 114

Qwen 3.6 — quantized

Quantized GGUF, MLX, and FP8/FP4 packs of the Qwen 3.6 model family.

majentik/Qwen3.6-27B-MLX-2bit

Image-Text-to-Text • 28B • Updated Aug 10 • 104
majentik/Qwen3.6-27B-MLX-3bit

Image-Text-to-Text • 28B • Updated Aug 10 • 148 • 1
majentik/Qwen3.6-27B-MLX-4bit

Image-Text-to-Text • 28B • Updated Aug 10 • 55
majentik/Qwen3.6-27B-MLX-5bit

Image-Text-to-Text • 28B • Updated Aug 10 • 27

Gemma 4 — quantized (GGUF + MLX)

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 Jul 20 • 68
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q2_K

Image-Text-to-Text • 25B • Updated Jul 20 • 399
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q3_K_M

Image-Text-to-Text • 25B • Updated Jul 20 • 84
majentik/gemma-4-26B-A4B-it-RotorQuant-GGUF-Q4_K_M

Image-Text-to-Text • 25B • Updated Jul 20 • 257 • 1