Back to Explore
Qwen: Qwen3 30B A3B Instruct 2507
Alibaba·Released 2025-07-29
Open Source30B131K ctxApache 2.0
About
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
Related Models
Pricing
Input
$0.05
per 1M tokens
Output
$0.19
per 1M tokens
Blended
$0.08
per 1M tokens
Cheaper than 86% of models. Median price is $0.67/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.08
Monthly
$2.53
vs. Similar Models
Granite 3.3 8B (Non-reasoning)
$0.09+1%
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
$0.09+2%
AllenAI: Olmo 2 32B Instruct
$0.09+4%
NVIDIA: Nemotron 3 Nano 30B A3B
$0.09+4%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
32K
tokens
24% of context
Context Window Comparison
DeepSeek: DeepSeek V3.2
131KSame
OpenAI: gpt-oss-120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame
Open Source
apache-2.030BGGUF / GPTQ / AWQ
Downloads
1.4M
Likes
819
VRAM (FP16)
24-48 GB
GPU
A6000 / M3 Ultra