OpenModelStats

TensorFold AI Models

Tracked by OpenModelStats since Oct 1, 2026 · View on Hugging Face ↗

Tracked models
66
Downloads 30D
68.7K
Total downloads
160.1K
Total likes
160
Gained 7D
0

Most downloaded

  1. 1Qwen3.8-Flash-Next-MLX-4bitOct 1, 20269,093
  2. 2DeepSeek-V4.1-Flash-MLX-2bit-MTPOct 1, 20267,172
  3. 3Qwen3.8-Flash-Next-MLX-4bit-MTPOct 1, 20266,631
  4. 4Qwen3.8-Flash-Next-MLX-oQ4-MTPOct 1, 20264,474
  5. 5GLM-5.3-Flash-MLX-4bit-MTPOct 1, 20264,264
  6. 6MiMo-V2.6-Flash-RL-MLX-4bit-MTPOct 1, 20263,776
  7. 7Qwen3.8-27B-MLX-4bitOct 1, 20262,815
  8. 8DeepSeek-V4-Flash-0731-MXFP4-MLXOct 1, 20262,786
  9. 9Qwen3.8-Flash-Next-MLX-oQ3-MTPOct 1, 20261,798
  10. 10GLM-5.3-Flash-MLX-oQ4-MTPOct 1, 20261,752

Recently updated

  1. 1detectra-v1Oct 1, 20260
  2. 2Solar-Open2-250B-MLX-8bitOct 1, 202679
  3. 3Solar-Open2-250B-MLX-6bitOct 1, 2026291
  4. 4Qwen3.8-Flash-Next-oQ8Oct 1, 20260
  5. 5Solar-Open2-250B-MLX-4bitOct 1, 202692
  6. 6Qwen3.8-Flash-Next-MLX-oQ8-MTPOct 1, 20261,502
  7. 7Qwen3.8-Flash-Next-MLX-oQ6-MTPOct 1, 2026960
  8. 8Qwen3.8-Flash-Next-MLX-oQ6Oct 1, 2026437
  9. 9Qwen3.8-Flash-Next-MLX-oQ4-MTPOct 1, 20264,474
  10. 10Qwen3.8-Flash-Next-MLX-oQ4Oct 1, 2026755

All models

All tracked models published by TensorFold
ModelDL 30D7D
Qwen3.8-Flash-Next-MLX-6bit-MTPtensorfold/qwen3.8-flash-next-mlx-6bit-mtp470—
Qwen3.8-27B-oQ2tensorfold/qwen3.8-27b-oq2465—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-oQ4tensorfold/nvidia-nemotron-3.5-lightning-30b-a3b-oq4450—
Qwen3.6-35B-A3B-MLX-4bit-MTPtensorfold/qwen3.6-35b-a3b-mlx-4bit-mtp444—
Qwen3.8-27B-oQ4tensorfold/qwen3.8-27b-oq4440—
Qwen3.8-Flash-Next-MLX-oQ6tensorfold/qwen3.8-flash-next-mlx-oq6437—
Ling-3.0-flash-oQ4tensorfold/ling-3.0-flash-oq4403—
Qwen3.8-27B-MLX-8bittensorfold/qwen3.8-27b-mlx-8bit384—
Ling-3.0-flash-oQ5tensorfold/ling-3.0-flash-oq5356—
Qwen3.8-27B-MLX-6bittensorfold/qwen3.8-27b-mlx-6bit344—
Nex-N2.5-mini-MLX-oQ4tensorfold/nex-n2.5-mini-mlx-oq4335—
Qwen3.8-27B-oQ8tensorfold/qwen3.8-27b-oq8320—
Nex-N2.5-mini-MLX-8bittensorfold/nex-n2.5-mini-mlx-8bit309—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-oQ6tensorfold/nvidia-nemotron-3.5-lightning-30b-a3b-oq6304—
NVIDIA-Nemotron-3.5-Lightning-30B-A3B-oQ8tensorfold/nvidia-nemotron-3.5-lightning-30b-a3b-oq8303—
Solar-Open2-250B-MLX-6bittensorfold/solar-open2-250b-mlx-6bit291—
Laguna-S-2.1-MLX-6bittensorfold/laguna-s-2.1-mlx-6bit279—
Nex-N2.5-mini-MLX-oQ8tensorfold/nex-n2.5-mini-mlx-oq8275—
Nex-N2.5-mini-MLX-oQ6tensorfold/nex-n2.5-mini-mlx-oq6274—
Nex-N2.5-mini-MLX-oQ2tensorfold/nex-n2.5-mini-mlx-oq2255—
Laguna-S-2.1-MLX-4bittensorfold/laguna-s-2.1-mlx-4bit248—
Ling-3.0-flash-MLX-8bittensorfold/ling-3.0-flash-mlx-8bit234—
Muse-Glimmer-30B-MLX-8bittensorfold/muse-glimmer-30b-mlx-8bit216—
Qwen3.8-27B-oQ6tensorfold/qwen3.8-27b-oq6208—
Nex-N2.5-mini-MLX-6bittensorfold/nex-n2.5-mini-mlx-6bit207—