Raw / Formatted
332 pulls
332 pulls
Raw / Formatted
qwen/qwen3-30b-a3b
The 30B parameter (MoE) version of the Qwen3 model family.
Trained for Ttool use
GGUF
MLX
Last Updated 1 day ago
CUSTOM FIELDS
Special features defined by the model author
Enable Thinking
: boolean
(default=true)
Controls whether the model will think before replying
README
Qwen3 30B A3B GGUF by qwen
Supports a context length of up to 131,072 tokens with YaRN (default 32k)
Supports /no_think to disable reasoning, just add it at the end of your prompt
MoE model with 3.3B activated weights, 128 total and 8 active experts
Supports both thinking and non-thinking modes withe enhanced reasoning in both for significantly enhanced mathematics, coding, and commonsense
Excels at creative writing, role-playing, multi-turn dialogues, and instruction following
Advanced agent capabilities and support for over 100 languages and dialects
SOURCES
The underlying model files this model uses
When you download this model, LM Studio picks the source that will best suit your machine (you can override this)
CONFIG
Custom configuration options included with this model