Text Generation
MLX
Safetensors
English
Chinese
qwen3
coding
research
deep thinking
256k context
Qwen3
All use cases
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
dwq
float32
finetune
emergent
Merge
conversational
4-bit precision
FYI: not showing in LMstudio.
#1
by bobig - opened
Something not right on the Hugginface side?
Missing file?
That is weird, must be some tag issue, I added the mlx tag—will check in the morning
Thanks for letting me know, sometimes it’s a small thing, just have to find it
Team Radermacher has it in the queue too
Yeah, that shows up now
I made some GGUFs of it, processed from BF16--same source
Fixed!
Thank you.
You are right, this model is a sweet combo of Small, fast, and sassy. Good personality base for an impotent killer robot.
Ling Mini: 200 TPS 15GB
Qwen 4b: 150 TPS 2GB