Text Generation
GGUF
English
Prototype
8X3B MOE
mixture of experts
reasoning
thinking
thoughts
deepseek
Mixture of Experts
context 128k
Llama 3.2 MOE
creative
creative writing
general usage
problem solving
brainstorming
solve riddles
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
story
writing
fiction
roleplaying
llama 3.2
mergekit
Merge
llama-3
llama-3.2
conversational
I need F16 quantization, please
#2
by
nikitayev
- opened
Hi!
Please always do 16 bit quanta. They give stable results.
Hey;
Uploading source within the next day, then F16 should appear with Ggufs at Mradermacher's massive repo.
He is usually pretty quick.
I don't generally upload F16 - except for smaller models - because of connection issues locally.