Qwen3 Coder Flash 30B-A3B Architecture
Back to Qwen3 Coder Flash 30B-A3B in the gallery
Alibaba Cloud
Coding-tuned Qwen model that keeps a straightforward grouped-query MoE stack instead of the newer hybrid-attention variants.
Architecture and specifications
- Scale
- 30B total, 3.3B active (11% active)
- Context (tokens)
- 262,144 native (1,048,576 with YaRN)
- License
- Apache License 2.0
- Date
- 2025-07-31
- Decoder type
- Sparse MoE
- Attention
- GQA
- Layer mix
- 48 GQA
- KV cache / token (bf16) info
- 96 KiB · Moderate
- Key detail
- Uses 128 experts with 8 active per token and a native 256k context window for coding workloads.
Training and benchmarks
- Pretraining data
- Not disclosed The 30B card omits a token count. The 7.5T figure in the initial Coder release describes the 480B model. Model card · Coder release
- Post-training methods
- Not disclosed The 30B card confirms post-training but does not give a separate method breakdown. Model card