Qwen3 30B-A3B — Specifications
| Developer | Alibaba |
|---|
| Type | LLM (MoE) |
|---|
| Modality | Text → Text |
|---|
| Parameters | 30B total / 3B active (MoE) |
|---|
| Context window | 128K |
|---|
| Max output | — |
|---|
| License | Apache 2.0 (open) |
|---|
| Open weights | ✅ Yes |
|---|
| Released | 2025 |
|---|
| Input price | $0.12 /1M |
|---|
| Output price | $0.5 /1M |
|---|
| API providers | Alibaba, OpenRouter, Ollama |
|---|
🖥️ Run it locally
| VRAM (4-bit) | ~18 GB |
|---|
| Minimum GPU | RTX 4090 24GB (Q4) — fast, 3B active |
|---|
Official page →
A mixture-of-experts Qwen3 with 30B total parameters but only ~3B active per token — near-32B quality at a fraction of the compute, very fast locally. Apache 2.0, 128K context.
