Qwen3 30B A3B Instruct 2507

Qwen · released 2025-07-29 · apache-2.0 license

Qwen3-30B-A3B-Instruct-2507 is Alibaba's updated non-thinking 30.5B (3.3B active) open-weight MoE (July 2025, Apache-2.0): GPQA 70.4, AIME25 61.3, MMLU-Pro 78.4, strong long context. Artificial Analysis index 15.

Key specs

TypeLocal open-weight
Parameters30.53B total · MoE, — active
Architectureqwen3_moe
Context window262K tokens
Knowledge cutoff2025-06-30
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond70.4%
SWE-bench Verified
AIME61.3%
MMLU-Pro78.4%
BFCL v3 (tool use)
Composite score7.25
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M19.2 GB17.7 GB262K

Strengths & weaknesses

Strengths: Strong general instruction-following and alignment; Good math for a non-thinking small MoE (AIME25 61.3); Excellent long context (RULER 86.8), 262K native

Weaknesses: Non-thinking; weaker on hard agentic tool-use; Aider-Polyglot coding (35.6) lags larger models