DeepSeek-V3 vs Kimi-K2-Instruct
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V3 | Kimi-K2-Instruct |
|---|---|---|
| Parameters | 684.5 B | 1,026.5 B |
| Architecture | DeepseekV3ForCausalLM | DeepseekV3ForCausalLM |
| Context length | 163,840 | 131,072 |
| Licence | — | other |
| Commercial use | Unknown | Unknown |
| Languages | — | — |
| Downloads 30d | 1,113,783 | 218,841 |
| Downloads all time | 21.0 M | 4.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-12-25 | 2025-07-11 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
1.2 M162 K
DeepSeek-V3
Kimi-K2-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
DeepSeek-V3 · fp16 @ 160K ctx
2,811.5 GB / 24 GB
Kimi-K2-Instruct · fp16 @ 128K ctx
3,596.1 GB / 24 GB