Embeddings
AXQ Qwen3-Embedding and Nemotron-3-Embed retrieval packs: MLX MXFP4/MXFP8 and CUDA NVFP4.
Sentence Similarity • 0.6B • Updated • 43Note Native AXQuant CUDA NVFP4 W4A4 retrieval pack. Two-GPU development checks; not certified.
AutomatosX/AX-Qwen3-Embedding-4B-CUDA-AXQ-NVFP4-W4A4
Sentence Similarity • 4B • Updated • 37Note Native AXQuant CUDA NVFP4 W4A4 retrieval pack. Two-GPU development checks; not certified.
AutomatosX/AX-Qwen3-Embedding-8B-CUDA-AXQ-NVFP4-W4A4
Sentence Similarity • 8B • Updated • 40Note Native AXQuant CUDA NVFP4 W4A4 retrieval pack. Two-GPU development checks; not certified.
AutomatosX/AX-Nemotron-3-Embed-1B-CUDA-AXQ-NVFP4-W4A4
Sentence Similarity • 1B • Updated • 36Note Native AXQuant CUDA NVFP4 W4A4 retrieval pack. Two-GPU development checks; not certified.
AutomatosX/AX-Nemotron-3-Embed-8B-CUDA-AXQ-NVFP4-W4A4
Sentence Similarity • 8B • Updated • 36Note Native AXQuant CUDA NVFP4 W4A4 retrieval pack. Two-GPU development checks; not certified.
AutomatosX/AX-Qwen3-Embedding-0.6B-MLX-AXQ-MXFP4
Feature Extraction • 0.6B • Updated • 48Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Qwen3-Embedding-0.6B-MLX-AXQ-MXFP8
Feature Extraction • 0.6B • Updated • 61Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Qwen3-Embedding-4B-MLX-AXQ-MXFP4
Feature Extraction • 4B • Updated • 61Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Qwen3-Embedding-4B-MLX-AXQ-MXFP8
Feature Extraction • 4B • Updated • 70Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP4
Feature Extraction • 8B • Updated • 73Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Qwen3-Embedding-8B-MLX-AXQ-MXFP8
Feature Extraction • 8B • Updated • 165Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP4
Feature Extraction • 1B • Updated • 34Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Nemotron-3-Embed-1B-MLX-AXQ-MXFP8
Feature Extraction • 1B • Updated • 30Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Nemotron-3-Embed-8B-MLX-AXQ-MXFP4
Feature Extraction • 8B • Updated • 40Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-Nemotron-3-Embed-8B-MLX-AXQ-MXFP8
Feature Extraction • 8B • Updated • 64Note AXQ retrieval pack (feature-extraction only). Not certified.
AutomatosX/AX-EmbeddingGemma-2-CUDA-AXQ-NVFP4-W4A16
Feature Extraction • 0.7B • Updated • 15Note Native AXQuant CUDA NVFP4 W4A16 EmbeddingGemma 2 pack. Activations stay BF16. Not certified.
AutomatosX/AX-EmbeddingGemma-2-MLX-AXQ-MXFP4
Feature Extraction • 0.7B • Updated • 18Note AXQ EmbeddingGemma 2 retrieval pack. Vision and audio towers stay BF16. Not certified.
AutomatosX/AX-EmbeddingGemma-2-MLX-AXQ-MXFP8
Feature Extraction • 0.7B • Updated • 80Note AXQ EmbeddingGemma 2 retrieval pack. Vision and audio towers stay BF16. Not certified.