サイト内検索

AI モデル 51

• Muse-Glimmer-30B-oQ4↗

  TensorFold

• Qwen3.8-27B-MLX-6bit↗

  TensorFold

• Laguna-S-2.1-MLX-4bit↗

  TensorFold

• Qwen3.8-Flash-Next-MLX-2bit-MTP↗

  TensorFold

  A compact MLX affine conversion of Qwen/Qwen3.8-Flash-Next with sensitive language paths kept in BF16 and the model's own MTP block preserved. This is a non-sensitivity MLX conversion. It is not uniform Q2 and it is not an oQ build. Routed and shared experts plus the predictive n-gram embedding paths use affine 2-bit weights at group size 32. Attention, Gated DeltaNet, hyperconnection, routing, vision, token embedding, output head, and native MTP weights remain in BF16 or their source-compatible dtype. The upstream tokenizer, current chat template, image and video processor configuration, generation configuration, licence, and native MTP configuration are included.

• Ling-3.0-flash-MLX-4bit↗

  TensorFold

• GLM-5.3-Flash-MLX-oQ2-MTP↗

  TensorFold

• MiniCPM-V-4.7-35B-A3B-MLX-4bit-TensorFold↗

  kuepker

• GLM-5.3-Flash-MLX-oQ4-MTP↗

  TensorFold

• NVIDIA-Nemotron-3.5-Lightning-30B-A3B-oQ8↗

  TensorFold

• NVIDIA-Nemotron-3.5-Lightning-30B-A3B-MLX-6bit↗

  TensorFold