Qwen3 235B A22B

Qwen · released 2025-04-27 · apache-2.0 license

Qwen3 235B A22B by Qwen — 235.09B MoE (22B active) open-weight local LLM. License: apache-2.0. Benchmarks, VRAM requirements per quantization, GPU compatibility, pricing and community reviews on slopsome.com.

Key specs

TypeLocal open-weight
Parameters235.09B total · MoE, 22B active
Architectureqwen3_moe
Context window41K tokens
Knowledge cutoff2025-02-01
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond71%
SWE-bench Verified62%
AIME85%
MMLU-Pro83%
BFCL v3 (tool use)73%
Composite score6.88
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q8240 GB235 GB256 GB131K
Q4_K_M137.9 GB136.4 GB160 GB41K

API pricing (per 1M tokens)

ProviderInputOutputFree tier
Together AI$0.2$0.6No
Fireworks AI$0.22$0.88No
SiliconFlow$0.35$1.4No