Qwen3.5-9B vs Kimi-K2.5
Specs, VRAM requirements and download trends — updated 28 July 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.5-9B | Kimi-K2.5 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 9.7 B | 1,058.6 B |
| Architecture | Qwen3_5ForConditionalGeneration | KimiK25ForConditionalGeneration |
| Context length | 262,144 | 256,000 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 6,366,157 | 803,810 |
| Downloads all time | 75.3 M | 15.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-02-27 | 2026-01-01 |
| API input price / 1M tokens | $0.17 | $0.53 |
| API output price / 1M tokens | $0.25 | $3.33 |
| Est. cost per 1M input + 1M output tokens | $0.42 | $3.86 |
| Cached input / 1M tokens | — | $0.21 |
| AA Intelligence Index | — | — |
| AA Coding Index | 28.7 | 46.8 |
| AA Agentic Index | 1.2 | — |
| Max output tokens | 235,929 | 65,536 |
| API providers | 6 | 5 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3.5-9B
$0.42
Kimi-K2.5
$3.86
Qwen3.5-9B is 9.2× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
14.3 M804 K
Qwen3.5-9B
Kimi-K2.5
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.5-9B · fp16
23.2 GB / 24 GB
Kimi-K2.5 · fp16
814.0 GB / 24 GB