Qwen3-Coder-30B-A3B-Instruct
Qwen3-Coder is available in multiple sizes. Today, we're excited to introduce Qwen3-Coder-30B-A3B-Instruct. This streamlined model maintains impressive performance and efficiency, featuring the following key enhancements:
Params
30.5 B
Context
262,144
Downloads 30d
569 K
Likes
1,248
Download history
daily snapshots · 55 days
▲ 497 K in the last 30 days (46.6%)
1.0 M569 K
Aug 22Sep 1Sep 11Sep 20
1.5 M569 K
Jul 28Aug 15Sep 2Sep 20
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 61.1 GB | 72.3 GB | ❌ Won’t fit |
| model.safetensors (bf16, full) | bf16 + 256K ctx | 61.1 GB | 214.2 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Run it
copy-paste, exact tags checked against the Hub$ curl -s https://aimodelscomparison.com/api/v1/models/qwen3-coder-30b-a3b-instruct
{
"hf_id": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
"params_b": 30.53,
"context_length": 262144,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 569071,
"vram_estimates": [
{ "quant": "bf16", "gb": 72.3 }
],
"updated_at": "2026-07-28T18:03:07Z"
}
Specifications
- Architecture
- Qwen3MoeForCausalLM
- Parameters
- 30.5 B
- Tensor type
- BF16
- Context length
- 262,144
- Vocabulary
- 151,936
- Layers / heads
- 48 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-07-31
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Compare with any text-generation model