Skip to content
DeepSeek

DeepSeek v2 Chat

Maker’s page
Check price at Amazon for DeepSeek DeepSeek-V2-Chat (affiliate link, opens in new tab)
Weights at 16-bit
471 GB
Weights at 8-bit (Q8_0)
250 GB
Weights at 4-bit (Q4_K_M)
143 GB
Smallest card at 4-bit
More than one card
Parameters
Layers
KV heads
Context
Licence

Specs

Attention heads
Context
Downloads (30 days)
Experts
Experts per token
Hidden size
KV heads
KV latent rank (MLA)
Layers
Licence
Parameters
Parameters by type
Publisher
RoPE key size (MLA)
Shared experts
Task

More from DeepSeek