Qwen3-14B vs Qwen2.5-Coder-32B-Instruct
Specs, VRAM requirements and download trends — updated 23 October 2026.
Qwen · B · Open weights
Params
32.8 B
Context
32,768
30d
588 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-14B | Qwen2.5-Coder-32B-Instruct |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 14.8 B | 32.8 B |
| Architecture | Qwen3ForCausalLM | Qwen2ForCausalLM |
| Context length | 40,960 | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 9,211,389 | 588,474 |
| Downloads all time | 37.8 M | 13.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2024-11-06 |
| API input price / 1M tokens | $0.12 | $0.66 |
| API output price / 1M tokens | $0.24 | $1.00 |
| Est. cost per 1M input + 1M output tokens | $0.36 | $1.66 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | 6.7 | 6.7 |
| AA Coding Index | — | — |
| AA Agentic Index | — | — |
| Max output tokens | 16,384 | 29,491 |
| API providers | 2 | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-14B
$0.36
Qwen2.5-Coder-32B-Instruct
$1.66
Qwen3-14B is 4.6× cheaper at list price.
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
9.2 M588 K
Qwen3-14B
Qwen2.5-Coder-32B-Instruct
A overtook B on 5 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-14B · fp16
35.2 GB / 24 GB
Qwen2.5-Coder-32B-Instruct · fp16
77.5 GB / 24 GB