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.

Qwen3 Coder Flash 30B-A3B architecture diagram
Qwen3 Coder Flash 30B-A3B architecture diagram. Select the diagram to view it at full size.

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
AA Intelligence Index v4.3.2 info
Total score 9.6 General N/A Scientific 1.9 Coding N/A Agents N/A

Further reading and tools