Model
Model explorer
Qwen3-30B-A3B (Non-Thinking)
OPENAlibaba · Qwen3 family · released Apr 29, 2025
Same MoE weights as thinking mode, with the reasoning trace disabled for fast low-latency chat.
ReasoningCodingVisionFunction callingTool useAgentic
1101.1
Elo · rank #191
Parameters
30.5B
Active params
3.3B (MoE)
Context
128K tokens
Architecture
MoE, 128 experts / 8 active (fine-grained, no shared experts)
License
Apache 2.0
Languages
119+
API price (in/out)
$0.108 / $0.431
Modalities
text
Benchmark results
Bar shows position within the tracked field; marker = field best
best: GPT-5.2 · 100.0%
best: Qwen3-235B-A22B (Non-Thinking) · 96.1%
best: Hunyuan-A13B · 78.3%
best: Qwen3.6-Plus · 93.3%
best: DeepSeek-V4-Pro (Think Max) · 3206
best: GPT-5.6 · 94.6%
best: Gemma 4 26B A4B · 98.5%
best: DeepSeek-V4-Pro (Think Max) · 93.5%
best: GPT-5 · 99.4%
best: Qwen3.7-Max · 95.0%
best: Gemini 3.1 Pro · 92.6%
Run it locally
VRAM @ Q4
18.6 GB
VRAM @ FP16
61 GB
Fits on (Q4)
RTX 3090 24GBRTX 4090 24GBRTX 5090 32GBM4 Pro 48GBM3 Max 128GBM3 Ultra 512GBA100 80GBH100 80GBH200 141GBB200 192GB
Throughput data unavailable.
Quantizations
GGUF · AWQ · GPTQ · MLX
Qwen3 family
Elo progression across releases
Qwen3-14B (Non-Thinking)Apr 20251094.6Qwen3-14B (Thinking)Apr 20251396.5Qwen3-235B-A22B (Non-Thinking)Apr 20251235.2Qwen3-235B-A22B (Thinking)Apr 20251536.2Qwen3-30B-A3B (Non-Thinking)Apr 20251101.1Qwen3-30B-A3B (Thinking)Apr 20251483.2Qwen3-32B (Non-Thinking)Apr 20251121.8Qwen3-32B (Thinking)Apr 20251509.2Qwen3-8B (Non-Thinking)Apr 2025922.1Qwen3-8B (Thinking)Apr 20251323.0Qwen3-235B-A22B-Instruct-2507Jul 20251591.0Qwen3-235B-A22B-Thinking-2507Jul 20251842.4
API price $0.108/$0.431 · each benchmark row carries its own source badge (see methodology)