DeepSeek-V3.2 vs Kimi-K2-Instruct

Specs, VRAM requirements and download trends — updated 6 August 2026.

deepseek-ai · A
Params
685.4 B
Context
163,840
30d
1.2 M
mit · commercial OK
moonshotai · B
Params
1,026.5 B
Context
131,072
30d
182 K

Specification comparison

Differences are highlighted; identical values are muted.

Specification DeepSeek-V3.2 Kimi-K2-Instruct
Parameters 685.4 B 1,026.5 B
Architecture DeepseekV32ForCausalLM DeepseekV3ForCausalLM
Context length 163,840 131,072
Licence mit other
Commercial use Allowed Unknown
Languages
Downloads 30d 1,246,445 182,313
Downloads all time 21.3 M 3.8 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-12-01 2025-07-11

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

1.3 M168 K
DeepSeek-V3.2 Kimi-K2-Instruct

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

DeepSeek-V3.2 · fp16 @ 160K ctx 2,815.1 GB / 24 GB
❌ Won’t fit
Kimi-K2-Instruct · fp16 @ 128K ctx 3,596.1 GB / 24 GB
❌ Won’t fit

Adjacent comparisons