OpenModelStats

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit

Duckets/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit

Image Text to Text74.9B parametersmlx-vlmLicense: other
Tracked by OpenModelStats since October 16, 2026View on Hugging Face ↗
Downloads 30D
823
Total downloads
823
Gained 7D
—
Gained 30D
—
Likes
2
Rank · tracked models
#38,070
634(up 634 places)this week
Parameters
74.9B
Last source update
Oct 17, 2026
  • It moved from #3726 to #3648 among tracked Image Text to Text models this week.
7D30D90D1YAll
Total downloadsGained per dayRolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit is a image text to text model published by Duckets. OpenModelStats has tracked the model since Oct 16, 2026, most recently observing it 30h ago.

Published
Oct 15, 2026
Last updated
Oct 17, 2026
Library
mlx-vlm
License
other
Task
Image Text to Text
Parameters
74,885,081,094
Spaces
—
Derivative models
—
Velocity 7D/day
—
mlx-vlmsafetensorsnemotron_h_omnimlxapple-siliconquantized4-bitnemotronnemotron-hmoevisionimage-text-to-text

Publisher

DucketsView publisher statistics →

Derived from nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16 (reported by the source; parent not yet tracked).

Similar models

Models similar to NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-4bit
ModelDL 30D
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16nvidia3,817
NVIDIA-Nemotron-3.5-Bolt-74B-A9B-AWQ-INT4cyankiwi27
Qwen3.5-122B-A10B-NVFP4unsloth33.2K
Qwen3.8-Flash-Next-W4A16-AutoRoundIntel19.8K
Qwen3.8-Flash-Next-W4A16-RTN-AutoRoundIntel502
Qwen3.8-Flash-Next-Uncensored-W4A16-AutoRound-INT8PLE-MTPMochgolf305