view post Post 124 Feels good to get the result I did on Anansi. Literally exactly what I hoped for, from the merge, which rarely happens. Makes the potato feel less potato-y. See translation
view post Post 3047 Good news, llama.cpp seems to be close to supporting MTP on qwen models. Bad news, every single gguf will have to be redone when it is. See translation
My own merges for RP on mobile dGPU I think these are pretty pretty good. BlueNipples/Anansi-35B-A3B-Q8-Prose-GGUF Text Generation • 35B • Updated 12 days ago • 1.46k • 1 mradermacher/LucidVitality-9b-i1-GGUF 9B • Updated 19 days ago • 3.24k • 1
My own merges for RP on mobile dGPU I think these are pretty pretty good. BlueNipples/Anansi-35B-A3B-Q8-Prose-GGUF Text Generation • 35B • Updated 12 days ago • 1.46k • 1 mradermacher/LucidVitality-9b-i1-GGUF 9B • Updated 19 days ago • 3.24k • 1