Qwen3-30B-A3B-Instruct-2507 vs Qwen2.5-72B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 25 August 2026.
Qwen · A · Open weights
Params
30.5 B
Context
262,144
30d
896 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-30B-A3B-Instruct-2507 | Qwen2.5-72B-Instruct-AWQ |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 30.5 B | 73.0 B |
| Architecture | Qwen3MoeForCausalLM | Qwen2ForCausalLM |
| Context length | 262,144 | 32,768 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 895,719 | 252,438 |
| Downloads all time | 18.8 M | 12.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-07-28 | 2024-09-17 |
| API input price / 1M tokens | $0.10 | not on OpenRouter |
| API output price / 1M tokens | $0.30 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.40 | not on OpenRouter |
| Cached input / 1M tokens | $0.10 | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 235,929 | not on OpenRouter |
| API providers | 3 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | No | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-30B-A3B-Instruct-2507
$0.40
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.9 M252 K
Qwen3-30B-A3B-Instruct-2507
Qwen2.5-72B-Instruct-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-72B-Instruct-AWQ · fp16
57.2 GB / 24 GB
Qwen3-30B-A3B-Instruct-2507 · fp16 @ 256K ctx
214.2 GB / 24 GB