txgsync/nslm-qwen38
908 GB
Matthew P Barnson PRO
txgsync
AI & ML interests
I like to noodle with models and see what weird things I can do with them.
Recent Activity
updated a model about 14 hours ago
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P3 updated a model about 14 hours ago
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P4 updated a model about 14 hours ago
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ3Organizations
Qwen3.8-Flash-Next for home GPUs and Macs: trellis and SeedLM experts (NanoSeedLM, mlx-vlm, oMLX), and MLX mixed precision (oQe, MXFP4)
-
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P4
Image-Text-to-Text • 97B • Updated • 230 • 1 -
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P3
Image-Text-to-Text • 89B • Updated • 419 • 1 -
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ4
Image-Text-to-Text • 57B • Updated • 117 -
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ3-D4
Image-Text-to-Text • 57B • Updated • 125 • 1
NVIDIA Nemotron 3.5 Bolt, unchanged, with MLX model files for oMLX and mlx-vlm. Vision included. LiLiCorr version: speculative decoding in oMLX.
-
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-MLX
Image-Text-to-Text • 23B • Updated • 861 • 1 -
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
Image-Text-to-Text • 25B • Updated • 16.1k • 172 -
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
Image-Text-to-Text • 75B • Updated • 8.59k • 52 -
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-MLX
Image-Text-to-Text • 23B • Updated • 656
Qwen3.8-Flash-Next for home GPUs and Macs: trellis and SeedLM experts (NanoSeedLM, mlx-vlm, oMLX), and MLX mixed precision (oQe, MXFP4)
-
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P4
Image-Text-to-Text • 97B • Updated • 230 • 1 -
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P3
Image-Text-to-Text • 89B • Updated • 419 • 1 -
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ4
Image-Text-to-Text • 57B • Updated • 117 -
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ3-D4
Image-Text-to-Text • 57B • Updated • 125 • 1
NVIDIA Nemotron 3.5 Bolt, unchanged, with MLX model files for oMLX and mlx-vlm. Vision included. LiLiCorr version: speculative decoding in oMLX.
-
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-MLX
Image-Text-to-Text • 23B • Updated • 861 • 1 -
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB
Image-Text-to-Text • 25B • Updated • 16.1k • 172 -
nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-BF16
Image-Text-to-Text • 75B • Updated • 8.59k • 52 -
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-MLX
Image-Text-to-Text • 23B • Updated • 656
models 26
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P3
Image-Text-to-Text • 89B • Updated • 419 • 1
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-P4
Image-Text-to-Text • 97B • Updated • 230 • 1
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ3
Image-Text-to-Text • 57B • Updated • 125
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ3-D4
Image-Text-to-Text • 57B • Updated • 125 • 1
txgsync/Qwen3.8-Flash-Next-NanoSeedLM-TCQ4
Image-Text-to-Text • 57B • Updated • 117
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-LiLiCorr-MLX
Image-Text-to-Text • 23B • Updated • 656
txgsync/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB-MLX
Image-Text-to-Text • 23B • Updated • 861 • 1
txgsync/K2-Horizon-MoVA-36B-A4B-MLA-NanoSeedLM-P3
Text Generation • 10B • Updated • 188
txgsync/K2-Horizon-MoVA-36B-A4B-MLA-NanoSeedLM-P4
Text Generation • 12B • Updated • 165
txgsync/K2-Horizon-MoVA-36B-A4B-MLA-oQ4e
Text Generation • 38B • Updated • 115