Compare LLM Models

Select 2-5 models to compare side by side.

Select models to compare 0 / 5 selected

Top downloads

🤖 DeepSeek-V4-Pro-0813 deepseek-ai 🤖 GLM-5.3 zai-org 🤖 Kimi-K3 moonshotai

Select 2-5 models

Attribute	🤖 Qwen3-14B-AWQ Qwen
Company	Qwen
Release Date	2025-05-01
Parameters (B)	14.8
Architecture	Transformer
Context Window	128000
Input Modalities	text
Open Source	Yes
License	apache-2.0
Score	0
VRAM (GB)	10
Compute	Single NVIDIA GPU with ≥10GB VRAM (e.g., RTX 3060 12GB, RTX 4070); CUDA required. Supports AWQ 4-bit inference via transformers, vLLM (≥0.8.5), or SGLang (≥0.4.6).
Benchmark: AIME-2024	77
Benchmark: GPQA	62.1
Pricing (Input)	—
Pricing (Output)	—