MLX Embedding Quantization Matrix - Q, oQ, oQe at 4/6/8-bit Thirty public MLX embedding checkpoints with explicit BF16 provenance, Q/oQ/oQe lineage, and matched representation-fidelity evaluation. TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q4 Feature Extraction • 93.1M • Updated 1 day ago TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4 Feature Extraction • 96.8M • Updated 1 day ago TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4e Feature Extraction • 96.8M • Updated 1 day ago TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q6 Feature Extraction • 0.1B • Updated 1 day ago
MLX Embedding Quantization Matrix - Q, oQ, oQe at 4/6/8-bit Thirty public MLX embedding checkpoints with explicit BF16 provenance, Q/oQ/oQe lineage, and matched representation-fidelity evaluation. TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q4 Feature Extraction • 93.1M • Updated 1 day ago TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4 Feature Extraction • 96.8M • Updated 1 day ago TiGa-RCE/Qwen3-Embedding-0.6B-MLX-oQ4e Feature Extraction • 96.8M • Updated 1 day ago TiGa-RCE/Qwen3-Embedding-0.6B-MLX-Q6 Feature Extraction • 0.1B • Updated 1 day ago
Running on Zero Agents Embedding Quantization CUDA Control 🔬 Run embedding benchmark and see performance metrics