Qwen3-30B-A3B-GPTQ-Int4
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support, with the following key features:
Params
30.5 B
Context
40,960
Downloads 30d
208 K
Likes
57
Download history
daily snapshots · 56 days
▲ 137 K in the last 30 days (39.6%)
404 K208 K
Aug 23Sep 2Sep 12Sep 21
404 K166 K
Jul 28Aug 15Sep 3Sep 21
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 | i32 | 16.9 GB | 23.7 GB | ⚠️ Tight — reduce context |
| model.safetensors (bf16, full) | bf16 + 40K ctx | 16.9 GB | 42.0 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/qwen3-30b-a3b-gptq-int4
{
"hf_id": "Qwen/Qwen3-30B-A3B-GPTQ-Int4",
"params_b": 30.53,
"context_length": 40960,
"license": { "id": "apache-2.0", "commercial": "yes" },
"downloads_30d": 208307,
"vram_estimates": [
{ "quant": "i32", "gb": 23.7 }
],
"updated_at": "2026-07-28T18:08:49Z"
}
Specifications
- Architecture
- Qwen3MoeForCausalLM
- Parameters
- 30.5 B
- Tensor type
- I32
- Context length
- 40,960
- Vocabulary
- 151,936
- Layers / heads
- 48 / 32
- Licence
- apache-2.0
- First seen on the Hub
- 2025-05-05
- Base model
- Qwen3-30B-A3B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Compare with any text-generation model