Gemma 3n fixes for GGUFs and Ollama
pinned❤️
2
1
#6 opened about 8 hours ago
by
shimmyshimmer

Cannot offload token_embd layers to CUDA
#4 opened 2 days ago
by
WBB2500
Multimodal support
2
#2 opened 3 days ago
by
Nasa1423