surogate/Qwen3-4B-FP8
Text Generation • 4B • Updated • 8
AI & ML interests
Insanely fast LLM pre-training and fine-tuning for modern NVIDIA GPUs.
Recent Activity
surogate/Qwen3-0.6B-Base
Text Generation • 0.6B • Updated • 4
surogate/Qwen3-0.6B-FP8
Text Generation • 0.8B • Updated • 9
surogate/Qwen3-14B-NVFP4
Text Generation • 8B • Updated • 19
surogate/Qwen3-32B-NVFP4
Text Generation • 17B • Updated • 23
surogate/Llama-3.3-70B-Instruct-NVFP4
41B • Updated • 4
surogate/Qwen3-Next-80B-A3B-Instruct-NVFP4
Text Generation • Updated • 9
surogate/Qwen3-Next-80B-A3B-Thinking-NVFP4
Text Generation • Updated • 9
surogate/Qwen3-30B-A3B-NVFP4
Text Generation • 16B • Updated • 8
surogate/Qwen3-8B-NVFP4
Text Generation • 5B • Updated • 11 • 1
surogate/gemma-3-270m-it-NVFP4
0.4B • Updated • 4
surogate/Qwen3-0.6B-AWQ
0.8B • Updated • 8
surogate/Qwen3-30B-A3B-AWQ
Text Generation • 31B • Updated • 183