Home
About
Pricing
Documentation
Articles
Early Access
Qwen3-Coder-30B-A3B-Instruct-GGUF
Home
/
Recommended Models
/ Qwen3-Coder-30B-A3B-Instruct-GGUF
Qwen3-Coder-30B-A3B-Instruct-GGUF
Author
unsloth
Parameters
30B
Quantization
Q5_K_M
Format
GGUF
Use on Infersec
View on HuggingFace
Strengths
MBPP+
: 88.6% (335/378)
BFCL
(tool calling): 62.0% (400 problems)
Tested Hardware
Benchmarked by Infersec on:
NVIDIA RTX 5090
(64 GB RAM, 32 GB VRAM, linux)
Benchmark Runs
Performance and quality results across different hardware configurations
NVIDIA RTX 5090
64 GB RAM
linux
c=2 p=1
133.4 tok/s
MBPP+ 88.6% · BFCL 62.0%
Scroll to top