Qwen2.5-Coder-14B-Instruct-AWQ vs phi-4
Specs, VRAM requirements and download trends — updated 10 September 2026.
Qwen · A · Open weights
Params
14.8 B
Context
32,768
30d
332 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-Coder-14B-Instruct-AWQ | phi-4 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 14.8 B | 14.7 B |
| Architecture | Qwen2ForCausalLM | Phi3ForCausalLM |
| Context length | 32,768 | 16,384 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 1 |
| Downloads 30d | 332,449 | 356,282 |
| Downloads all time | 8.0 M | 14.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-11-09 | 2024-12-11 |
| API input price / 1M tokens | not on OpenRouter | $0.07 |
| API output price / 1M tokens | not on OpenRouter | $0.14 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.21 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | 5.9 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 14,745 |
| API providers | not on OpenRouter | 1 |
| Tool calling | not on OpenRouter | No |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
phi-4
$0.21
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
1.9 M332 K
Qwen2.5-Coder-14B-Instruct-AWQ
phi-4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-14B-Instruct-AWQ · fp16
13.7 GB / 24 GB
phi-4 · fp16
34.9 GB / 24 GB