NVFP4 experts for Blackwell, calibrated by NVIDIA's recipe and measured against the original: checkpoint plus the metrics.
AI & ML interests
Local Models Server and Free Ai Chat app
Recent Activity
View all activity
Organization Card
👋 Hi!
Run AI models and agents locally with TurboQuant in Atomic Chat.
Become one of 150+ contributors on GitHub and chat with the Atomic team on Discord.
models 95
AtomicChat/DeepSeek-V4.1-Flash-NVFP4-nvidia
Text Generation • 763B • Updated • 668 • 5
AtomicChat/Ling-3.0-flash-VL-GGUF
Image-Text-to-Text • 124B • Updated • 1.84k • 8
AtomicChat/Ling-3.0-flash-Fin-GGUF
Text Generation • 127B • Updated • 361 • 4
AtomicChat/GLM-5.3-GGUF
Text Generation • Updated • 2
AtomicChat/Qwen3.8-Flash-Next-GGUF
Text Generation • 177B • Updated • 226k • 138
AtomicChat/GLM-5.3-Flash-GGUF
Text Generation • Updated • 17
AtomicChat/Qwen3.8-27B-MLX-AD-5.00bpw-DWQ-17.7GB
Image-Text-to-Text • 27B • Updated • 424
AtomicChat/Qwen3.8-27B-MLX-AD-3.80bpw-DWQ-13.7GB
Image-Text-to-Text • 27B • Updated • 599 • 1
AtomicChat/Qwen3.8-27B-MLX-AD-3.70bpw-DWQ-13.4GB
Image-Text-to-Text • 27B • Updated • 1.07k • 3
AtomicChat/Qwen3.8-27B-MLX-AD-4.50bpw-DWQ-16.0GB
Image-Text-to-Text • 27B • Updated • 298
datasets 11
AtomicChat/DeepSeek-V4.1-Flash-NVFP4-metrics
Updated • 390 • 1
AtomicChat/calib-corpora
Preview • Updated • 638 • 7
AtomicChat/Qwen3.8-Flash-Next-GGUF-metrics
Viewer • Updated • 5 • 311
AtomicChat/Qwen3.8-27B-MLX-metrics
Updated • 228
AtomicChat/Qwen3.8-27B-GGUF-metrics
Updated • 8.21k • 4
AtomicChat/Ornith-1.5-35B-A3B-GGUF-metrics
Updated • 599 • 1
AtomicChat/Ornith-1.5-9B-GGUF-metrics
Viewer • Updated • 48 • 573 • 1
AtomicChat/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF-metrics
Updated • 99
AtomicChat/Muse-Glimmer-30B-GGUF-metrics
Viewer • Updated • 587k • 745
AtomicChat/Ling-3.0-flash-GGUF-metrics
Updated • 388