Qwen 3 30B-A3B
By Alibaba · China
Updated 2026-07-13
Overview
Alibaba's Qwen 3 MoE with 30B total and just 3B active parameters, supporting hybrid thinking mode. MMLU 81.4, AIME24 80.4, 100+ languages, Apache 2.0.
When to pick this model
- Fast self-hosted chat that toggles into reasoning when needed
- Multilingual production across 100+ languages
- Workloads needing reasoning quality without the verbosity of dedicated reasoners
- Single 24GB GPU deployments wanting MoE inference speed
VRAM requirements by quantization
| Quantization | VRAM required |
|---|---|
| Q4_K_M (recommended) | 19 GB |
| Q5_K_M | 23 GB |
| Q8_0 | 35 GB |
| FP16 (no quantization) | 62 GB |
VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.
In practice, Qwen 3 30B-A3B wants a 24 GB card at Q4_K_M (19 GB). Stepping up to Q8_0 nearly doubles the footprint to 35 GB, and unquantized FP16 weights take 62 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.
Without a GPU, Qwen 3 30B-A3B needs roughly 32 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 15 tokens/sec on entry-level GPUs, on the order of 40 tokens/sec on a mid-range card, and up to 100 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.
What hardware do you need
The table below matches Qwen 3 30B-A3B to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.
| GPU memory | Example cards | Best fit for Qwen 3 30B-A3B |
|---|---|---|
| 8 GB | RTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GB | Does not fit — needs 19 GB at Q4_K_M |
| 12 GB | RTX 5070, RTX 5070 Ti Laptop, RTX 4080 Laptop | Does not fit — needs 19 GB at Q4_K_M |
| 16 GB | RTX 5080, RTX 4080 Super, Radeon RX 9070 XT | Does not fit — needs 19 GB at Q4_K_M |
| 24 GB | RTX 4090, Radeon RX 7900 XTX, RTX 5090 Laptop | Q5_K_M (23 GB used) |
| 32 GB | RTX 5090 | Q5_K_M (23 GB used) |
Which GPU should you buy to run Qwen 3 30B-A3B?
To run Qwen 3 30B-A3B locally at Q4, you need ~19 GB of VRAM. The best value for this is a RTX 4090 (24 GB VRAM).
As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.
Published benchmark scores
| Benchmark | Score |
|---|---|
| MMLU (base) | 81.38 |
| AIME 2024 | 80.4 |
Scores published by the model author or aggregated from public leaderboards. Re-measured monthly by our editorial team.
To put Qwen 3 30B-A3B in context: its AIME 2024 score of 80.4 ranks #2 of the 8 catalog models with a published AIME 2024 result (catalog median 71.7). Scores are author-published and measured under different harnesses, so treat gaps of a few points as noise rather than a verdict.
Strengths
- 3B active parameters keeps inference fast and cheap
- MMLU 81.4 and AIME24 80.4 — strong on both general and reasoning
- Apache 2.0
- Hybrid thinking toggle per request
- 100+ language coverage
Limitations
- ~19GB at Q4 — slightly tight on 16GB cards
- Thinking mode adds latency and token cost
- MoE routing complicates some fine-tuning workflows
Typical workloads
In our catalog grid, Qwen 3 30B-A3B is filed under Efficient Chat, Reasoning, Multilingual — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multi-step reasoning and math-flavoured tasks; multilingual workloads.
The 128k-token context window is large enough to hold entire codebases' worth of files or long reports in a single prompt, which is what makes local RAG and document analysis practical. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.
Architecture & training
Architecture: MoE 128 experts · 30B/3B active · hybrid thinking
Training: Qwen 3 base.
The most pragmatic Apache 2.0 model on the market — MoE speed, reasoning on demand, and one of the strongest 24GB-class options.
Quick start
ollama run qwen3:30b-a3bOr use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.
Similar models worth comparing
Frequently asked questions
How much VRAM does Qwen 3 30B-A3B need?
At the recommended Q4_K_M quantization, Qwen 3 30B-A3B needs about 19 GB of VRAM. Q8_0 takes 35 GB, and unquantized FP16 weights take 62 GB.
Can Qwen 3 30B-A3B run without a GPU?
Yes — with roughly 32 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.
What context window does Qwen 3 30B-A3B support?
Qwen 3 30B-A3B supports a 128k-token context window (131,072 tokens).
Can I use Qwen 3 30B-A3B commercially?
Yes. Qwen 3 30B-A3B is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.
How fast is Qwen 3 30B-A3B on consumer hardware?
Our compatibility engine estimates on the order of 40 tokens/sec on a mid-range GPU and up to 100 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.
Which quantization of Qwen 3 30B-A3B should I download first?
Start with Q4_K_M (19 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. On a 24 GB card you can run up to Q5_K_M.