Qwen · qwen3_moe · based on Qwen/Qwen3-30B-A3B-Base
Qwen3-30B-A3B
Qwen3-30B-A3B by Qwen: a 30.5B-parameter mixture-of-experts open-weight model under the apache-2.0 license with tool calling.
1,793,417 downloads · 945 likes · Model card · synced 2026-09-19
Specifications
- Parameters
- 30.5B (1.9B active)
- Architecture
- moe · qwen3_moe
- Layers
- 48
- Hidden size
- 2,048
- KV heads · head dim
- 4 · 128
- Vocabulary
- 151,936
- Native dtype
- bfloat16
- Context window
- 40,960 tokens
- Released
- 2025-04-27
- Last modified on Hub
- 2025-07-26
Features & licensing
- License
- apache-2.0
- Commercial use
- Yes
- Modalities
- text
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Languages
- EN
- Quantised variants on Hub
- FP8, GGUF, bitsandbytes
- Pipeline
- text-generation
Task fit
Editorial scores (0–100) used by the recommendation engine.
- Chat70
- RAG / Q&A70
- Code70
- Summarisation70
- Extraction70
- Agents70
Hardware to run Qwen3-30B-A3B
Weights need about 67 GB at FP16, 35 GB at INT8 and 20 GB at INT4. The KV cache adds roughly 98 MB per 1,000 tokens per request. For a reference workload of 5 requests per second with 1,500 input and 300 output tokens, total GPU memory is around 27.6 GB, which fits on 1 × NVIDIA A100 (80 GB).
| Configuration | VRAM | Utilisation | Est. first token | Cloud / month |
|---|---|---|---|---|
| 2 × NVIDIA L4 (24 GB) | 48 GB | 57 % | ~0.5 s | $1,168 |
| 1 × NVIDIA L40S (48 GB) | 48 GB | 57 % | ~0.2 s | $1,387 |
| 1 × NVIDIA A100 (80 GB)recommended | 80 GB | 34 % | ~0.1 s | $2,336 |
| 1 × NVIDIA H100 (80 GB) | 80 GB | 34 % | ~0.0 s | $3,285 |
Estimates only. Run an assessment for your own traffic.
Auto-imported from Hugging Face. Architecture, license and feature data are synced from the model repository; the task-fit scores below are provisional defaults until a curator reviews them.