Qwen3 235B A22B Instruct 2507

Qwen · released 2025-07-21 · apache-2.0 license

Qwen3-235B-A22B-Instruct-2507 is Alibaba's updated 235B (22B active) open-weight non-reasoning MoE (July 2025, Apache-2.0): MMLU-Pro 83.0, GPQA 77.5, AIME25 70.3. Artificial Analysis index 25.

Key specs

TypeLocal open-weight
Parameters235.09B total · MoE, — active
Architectureqwen3_moe
Context window262K tokens
Knowledge cutoff2025-06-30
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond77.5%
SWE-bench Verified
AIME70.3%
MMLU-Pro83%
BFCL v3 (tool use)
Composite score7.9
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M137.9 GB136.4 GB262K

Strengths & weaknesses

Strengths: Strong knowledge and instruction-following for a non-reasoning model; Very long context with high RULER (92.5); Apache-2.0

Weaknesses: Non-reasoning mode lags dedicated reasoners on hard math/coding; Verbose per Artificial Analysis