Skip to content

Qwen3 30B A3B Instruct 2507

by AlibabaRank #195Score 64.1

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...

Performance Overview

Score
64.1
Rank
#195
24h Change
0
7d Change
+65
State
stable
Confidence
high

Signal Scores

SignalNormalizedWeightContributionFreshness
Capabilities
capability
50.030%15.02026-08-08T12:29:26.950Z
Pricing
pricing_tier
99.825%25.02026-08-08T12:29:26.950Z
Context Window
context_window
86.015%12.92026-08-08T12:29:26.950Z
Recency
recency
64.615%9.72026-08-08T12:29:26.950Z
Output Capacity
output_capacity
74.815%11.22026-08-08T12:29:26.950Z

Top Drivers

positive
Pricing
$0.19/M output tokens
$0.19
neutral
Capabilities
Supports tools, JSON mode, streaming
3/7
positive
Context Window
262K token context window
262K
positive
Output Capacity
Up to 32K output tokens per request
32K

Capabilities

CapabilitySupported
VisionNo
ReasoningNo
JSON ModeYes
StreamingYes
Function CallingYes
Web SearchNo

Pricing

Input / 1M tokens
$0.05
Output / 1M tokens
$0.19
Context Window
262K
Max Output
32K

Related Models

Related

Qwen3 30B A3B Instruct 2507 Tracker - Performance History | LM Market Cap