Qwen3-Coder-30B-A3B-Instruct-GGUF
- Home
- / Recommended Models
- / Qwen3-Coder-30B-A3B-Instruct-GGUF
Qwen3-Coder-30B-A3B-Instruct-GGUF
VRAM needed
≈ 24 GB
Fits 24 GB+ consumer GPUs
Authorunsloth
Parameters30B
QuantizationQ5_K_M
FormatGGUF
Licenseapache-2.0
File size20.23 GB
Overview
Qwen3-Coder 30B A3B instruct - a coding specialist MoE tuned for code completion, refactoring, and agentic dev tasks. Needs 24 GB.
Recommended hardware
≈ 24 GB VRAM to run this 30B model at the Q5_K_M quantization.
Fits 24 GB+ consumer GPUs (e.g. RTX 3090, RTX 4090)