DeepSeek
Deepseek MoE 16B Base
Check price at Amazon for DeepSeek deepseek-moe-16b-base (affiliate link, opens in new tab)Affiliate link
- Weights at 16-bit
- 33 GB
- Weights at 8-bit (Q8_0)
- 17 GB
- Weights at 4-bit (Q4_K_M)
- 9.9 GB
- Smallest card at 4-bit
- Intel Arc B580 · 12 GB
- Parameters
- Layers
- KV heads
- Context
- Licence
Specs
- Attention heads
- Context
- Downloads (30 days)
- Experts
- Experts per token
- Head size
- Hidden size
- KV heads
- Layers
- Licence
- Parameters
- Parameters by type
- Publisher
- Shared experts
- Task
More from DeepSeek
- DeepSeek deepseek-coder-1.3b-instruct
- DeepSeek deepseek-coder-6.7b-base
- DeepSeek deepseek-coder-6.7b-instruct
- DeepSeek deepseek-coder-7b-instruct-v1.5
- DeepSeek DeepSeek-Coder-V2-Lite-Instruct
- DeepSeek deepseek-moe-16b-chat
- DeepSeek DeepSeek-R1
- DeepSeek DeepSeek-R1-0528
- DeepSeek DeepSeek-R1-0528-Qwen3-8B
- DeepSeek DeepSeek-R1-Distill-Llama-8B
- DeepSeek DeepSeek-R1-Distill-Llama-70B
- DeepSeek DeepSeek-R1-Distill-Qwen-1.5B