DevQuasar
/

deepseek-ai.DeepSeek-V3-Base-bf16

Text Generation

Model card Files Files and versions

Splitted by safetensor splitter

'Make knowledge free for everyone'

Downloads last month: 8

Safetensors

Model size

684B params

Tensor type

F32

·

BF16

·

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DevQuasar/deepseek-ai.DeepSeek-V3-Base-bf16

Base model

deepseek-ai/DeepSeek-V3-Base

Quantized

(2)

this model

Finetunes

1 model

Collection including DevQuasar/deepseek-ai.DeepSeek-V3-Base-bf16

Very Large GGUFs

GGUF quantized versions of very large models - over 100B parameters • 28 items • Updated 3 days ago • 3