← Back to Models

qwen3-coder-30b-a3b-instruct-mlx

qwen3-coder-30b-a3b-instruct-mlx

Publisher
lmstudio-community
Architecture
qwen3_moe(sparse)
Parameters
30B
Quantization
4bit (4.0 bpw)
Format
mlx
Max Context
262k tokens
Type
llm
File Size
16.01 GB
Est. RAM
17.5 GB
Est. VRAM
17.5 GB(~3B active)
Capabilities
trained_for_tool_use

Benchmark Results

Compare Models