Rust + CUDA engine that streams giant MoE models from SSD, running models far larger than VRAM. Mixed-precision GGUFs. github.com/giannisanni/pulsar
Gianni Sanrochman
giannisan
AI & ML interests
Transfromers, LLMs, multimodel, vision, audio
Recent Activity
new activity about 6 hours ago
giannisan/Laguna-S-2.1-ds4-gguf:Any chance of a larger quant that will run on pulsar? liked a model 2 days ago
giannisan/Laguna-S-2.1-ds4-gguf updated a collection 3 days ago
PulsarOrganizations
-
giannisan/penny-llama3-2x8b
Text Generation • 14B • Updated • 4 • 1 -
giannisan/penny5-dolphin-einstein-llama3-dare-ties-chatml
Text Generation • 8B • Updated • 5 • 1 -
giannisan/penny5-dolphin-einstein-llama3-dare-ties-chatml.gguf
8B • Updated • 17 • 1 -
mradermacher/penny-llama3-2x8b-v2-GGUF
14B • Updated • 95 • 1
Rust + CUDA engine that streams giant MoE models from SSD, running models far larger than VRAM. Mixed-precision GGUFs. github.com/giannisanni/pulsar
-
giannisan/penny-llama3-2x8b
Text Generation • 14B • Updated • 4 • 1 -
giannisan/penny5-dolphin-einstein-llama3-dare-ties-chatml
Text Generation • 8B • Updated • 5 • 1 -
giannisan/penny5-dolphin-einstein-llama3-dare-ties-chatml.gguf
8B • Updated • 17 • 1 -
mradermacher/penny-llama3-2x8b-v2-GGUF
14B • Updated • 95 • 1