Text Generation
Transformers
GGUF
64k context
high speed
all use cases
creative
creative writing
all genres
tool calls
tool use
problem solving
deep thinking
reasoning
deep reasoning
story
qwen3_moe
writing
fiction
roleplaying
bfloat16
role play
sillytavern
backyard
Lmstudio
Mixture of Experts
mixture of experts
4 experts activated
128 experts
NEO Imatrix
Max Imatrix
qwen3
imatrix
conversational
Will there be a similar fintune model of Qwen3 30b 2507?
#2
by
WilliamKing9
- opened
Qwen3 30b a3b 2507 was released and the thinking version might be released tomorrow. It performs better than the older versions, do you have a plan to fintune them?
Yes ; one is already uploaded: 53B , 42B is uploading as I write this.
https://huggingface.co/DavidAU/Qwen3-53B-A3B-2507-TOTAL-RECALL-v2-MASTER-CODER
(awaiting quanting)
Uploading ; 2 hours or so... then awaiting quanting...
https://huggingface.co/DavidAU/Qwen3-42B-A3B-2507-TOTAL-RECALL-v2-Medium-MASTER-CODER
NEO Imatrix (30b a3b 2507)
-> NEO Complete, awaiting quanting and upload.