Poor in Web Search
#2
by Drafvan - opened
I have a Q8_0 quant of this model running in Ollama through Openwebui. While it would search for things, it didn't actually use the information it found. Not quite sure where else to put this other than to let you know. Unsloth's Phi 4 on the LLM Leaderboard did even worse than Dyanka Preview however.