Home
About
Pricing
Documentation
Articles
Early Access
Qwen3-8B-GGUF
Home
/
Recommended Models
/ Qwen3-8B-GGUF
Qwen3-8B-GGUF
Author
Qwen
Parameters
8B
Quantization
Q4_K_M
Format
GGUF
Use on Infersec
View on HuggingFace
Strengths
HumanEval+
: 81.7% (134/164)
MBPP+
: 84.9% (321/378)
BFCL
(tool calling): 73.8% (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
155.8 tok/s
HumanEval+ 81.7% · MBPP+ 84.9% · BFCL 73.8%
Scroll to top