Qwen3-30B-A3B
Qwen3-30B-A3B is an open-weights language model from Qwen, released April 29, 2025. It has 31B parameters (mixture-of-experts, 3B active). The context window is 256K tokens. On the Epoch Capabilities Index it scores 134.1, rank 145 of 256 rated models.
Check it against your own PC →
Can you run Qwen3-30B-A3B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, GPU + experts in RAM, roughly 19 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 5.2 GB | 22.0 GB | ~19 |
| 8 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 7.2 GB | 20.0 GB | ~22 |
| 12 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 11.2 GB | 16.0 GB | ~27 |
| 16 GB VRAM | Runs · GPU + CPU experts | Q6_K (≈ lossless) | 15.2 GB | 12.0 GB | ~34 |
| 24 GB VRAM | Runs on GPU | Q4_K_M (very good) | 20.9 GB | – | ~230 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 27.2 GB | – | ~300 |
Ready-made quantizations on Hugging Face: unsloth/Qwen3-30B-A3B-Instruct-2507-GGUF · bartowski/Qwen_Qwen3-30B-A3B-Instruct-2507-GGUF · lmstudio-community/Qwen3-30B-A3B-Instruct-2507-GGUF · MaziyarPanahi/Qwen3-30B-A3B-Instruct-2507-GGUF · stelterlab/Qwen3-30B-A3B-Instruct-2507-AWQ · cyankiwi/Qwen3-30B-A3B-Instruct-2507-AWQ-4bit
Benchmark results
| Benchmark (Epoch AI) | Score |
|---|---|
| OTIS Mock AIME | 62.7% |
| GPQA Diamond | 50.9% |
Links
Hugging Face: Qwen/Qwen3-30B-A3B-Instruct-2507 · Epoch AI benchmarks
Models with a similar score
Qwen3-235B-A22B-Instruct (Jul 2025) · Grok 3 · Qwen3-32B · QwQ-32B · GPT-4.5 · GPT-4.1 · Qwen3-14B · Gemini 2.0 Pro
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash