Qwen3-30B-A3B
Q4 GGUF download: Qwen/Qwen3-30B-A3B-GGUF - 18.56 GB on disk, read 2026-09-27. VRAM figures above are estimates; this is the actual file size.
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
7.6
AA Index
Intelligence Index - Qwen3-30B-A3B vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Benchmark data from Artificial Analysis · updated 2026-10-19.
Hosted API cost & speed
What it costs to rent this model instead of running it locally
| Metric | Value |
|---|---|
| Input (per 1M tokens) | $0.14 |
| Output (per 1M tokens) | $0.55 |
| Median speed (hosted API) | 130 tok/s |
Median across hosted providers, measured by Artificial Analysis - updated 2026-10-19. Local llama.cpp speed depends on your hardware — see the hardware pages for estimates.
Arena rating (LMArena)
Human preference wins from head-to-head chat battles
| Metric | Value |
|---|---|
| Overall arena rating | 1317.0 |
| Rank (overall) | #239 |
| Battle votes | 26,157 |
Overall rating published by LMArena on 2026-10-15 - a pairwise human-preference Elo across live chat battles; higher is better. Fetched 2026-10-19. Open-weights models compete head-to-head with proprietary ones here — no benchmark prompts, just what people pick.
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve Qwen/Qwen3-30B-A3BNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Qwen3-30B-A3B
Qwen3-30B-A3B is a 30.5B-parameter apache-2.0 model from Qwen. At Q4_K_M it needs roughly 18 GB of VRAM, placing it in the 12-24gb hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 30.5B |
| Context length | 41K tokens |
| License | apache-2.0 |
| Modalities | text |
| Released | 2025-04-27 |
| Weights | Qwen/Qwen3-30B-A3B |
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~18 GB | RTX 3090, RTX 4090 |
| Q5_K_M | ~22 GB | RTX 3090, RTX 4090 |
| Q8_0 | ~33 GB | RTX 6000 Ada, dual RTX 3090 |
| FP16 | ~61 GB | A100 80GB, H100 |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve Qwen/Qwen3-30B-A3BPopularity
Qwen3-30B-A3B has 2,022,595 downloads in the last month on HuggingFace and 896 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Qwen3-30B-A3B need?
Qwen3-30B-A3B with 30.5B parameters needs approximately 18 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Qwen3-30B-A3B better than other Qwen models?
Qwen3-30B-A3B has 30.5B parameters with 40,960 context - a strong choice for general use.
What license is Qwen3-30B-A3B under?
Qwen3-30B-A3B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Qwen3-30B-A3B well?
With 30.5B parameters, Qwen3-30B-A3B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Qwen3-30B-A3B?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~22 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Qwen3-30B-A3B's context window handle?
Qwen3-30B-A3B supports a 40,960-token context window - enough for most medium-length documents and conversations. Real-world usable context may vary by implementation.
What models compete with Qwen3-30B-A3B?
Qwen3-30B-A3B competes with other 15B–46B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec