Qwen3-14B vs Qwen3-30B-A3B-Instruct-2507-AWQ
Specs, VRAM requirements and download trends — updated 24 October 2026.
stelterlab · B · Open weights
Params
30.8 B
Context
262,144
30d
411 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-14B | Qwen3-30B-A3B-Instruct-2507-AWQ |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 14.8 B | 30.8 B |
| Architecture | Qwen3ForCausalLM | Qwen3MoeForCausalLM |
| Context length | 40,960 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 9,401,416 | 410,570 |
| Downloads all time | 38.0 M | 844 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2025-08-02 |
| API input price / 1M tokens | $0.12 | not on OpenRouter |
| API output price / 1M tokens | $0.24 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.36 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | 6.7 | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 16,384 | not on OpenRouter |
| API providers | 2 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-14B
$0.36
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
9.4 M191 K
Qwen3-14B
Qwen3-30B-A3B-Instruct-2507-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-14B · fp16
35.2 GB / 24 GB
Qwen3-30B-A3B-Instruct-2507-AWQ · fp16 @ 256K ctx
166.5 GB / 24 GB