Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
niobures
/
Veena
like
0
ONNX
Safetensors
GGUF
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
No model card
Downloads last month
-
GGUF
Model size
4B params
Architecture
llama
Hardware compatibility
Log In
to view the estimation
1-bit
IQ1_S
1.41 GB
TQ1_0
1.27 GB
IQ1_M
1.48 GB
2-bit
IQ2_XXS
1.5 GB
IQ2_XS
1.58 GB
IQ2_S
1.61 GB
Q2_K_S
1.69 GB
TQ2_0
1.4 GB
Q2_K
1.6 GB
IQ2_M
1.66 GB
Q2_K_M
1.82 GB
3-bit
IQ3_XXS
1.8 GB
IQ3_XS
1.83 GB
IQ3_S
1.98 GB
Q3_K_S
2.02 GB
Q3_K_S
1.82 GB
IQ3_M
1.98 GB
Q3_K_M
2.15 GB
Q3_K_M
1.97 GB
Q3_K_L
2.1 GB
4-bit
IQ4_XS
2.16 GB
Q4_K_S
2.41 GB
Q4_K_S
2.27 GB
IQ4_NL
2.26 GB
Q4_0
2.14 GB
Q4_1
2.37 GB
Q4_0
2.26 GB
Q4_K_M
2.47 GB
Q4_K_M
2.36 GB
5-bit
Q5_K_S
2.77 GB
Q5_K_S
2.67 GB
Q5_0
2.61 GB
Q5_1
2.85 GB
Q5_0
2.67 GB
Q5_K_M
2.8 GB
Q5_K_M
2.73 GB
6-bit
Q6_K
3.11 GB
Q6_K_M
3.11 GB
8-bit
Q8_0
4.03 GB
Q8_0
4.03 GB
16-bit
BF16
7.58 GB
BF16_Q
5.92 GB
F16_Q
5.92 GB
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Collection including
niobures/Veena
TTS
Collection
16 items
•
Updated
Dec 2, 2025