Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
gghfez
/
DeepSeek-V3.1-Base-IQ2_KS
like
0
GGUF
gguf,
ik_llama.cpp
imatrix
conversational
License:
apache-2.0
Model card
Files
Files and versions
Community
Deploy
Use this model
gghfez/DeepSeek-V3.1-Base-IQ2_KS
This is the BASE model, not trained for conversations.
gghfez/DeepSeek-V3.1-Base-IQ2_KS
This is the BASE model, not trained for conversations.
Downloads last month
105
GGUF
Model size
672B params
Architecture
deepseek2
Chat template
Hardware compatibility
Log In
to view the estimation
2-bit
Q2_K
219 GB
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for
gghfez/DeepSeek-V3.1-Base-IQ2_KS
Base model
deepseek-ai/DeepSeek-V3.1-Base
Quantized
(
7
)
this model
Collection including
gghfez/DeepSeek-V3.1-Base-IQ2_KS
ik_llama quants
Collection
8 items
•
Updated
3 days ago