All Supported Models

29681 AI models · 198875 quantization formats tracked

P

P L M Team

1 models

PLM-1.8B-Instruct-gguf

1.8B 8K ctx
Q2_K
0.56GB file 2.59GB
Q3_K_L
0.79GB file 2.82GB
Q3_K_M
0.79GB file 2.82GB
Q3_K_S
0.79GB file 2.82GB
Q4_0
1.01GB file 3.04GB
Q4_1
1.01GB file 3.04GB
Q4_K_M
1.01GB file 3.04GB
Q4_K_S
1.01GB file 3.04GB
Q5_0
1.24GB file 3.27GB
Q5_1
1.24GB file 3.27GB
Q5_K_M
1.24GB file 3.27GB
Q5_K_S
1.24GB file 3.27GB
Q6_K
1.46GB file 3.49GB
Q8_0
1.91GB file 3.94GB
P

P O R T U L A N

2 models

gervasio-8b-portuguese-ptpt-decoder

8B 8K ctx
FP16
16GB file 18.13GB

gervasio-8b-portuguese-ptpt-decoder-quantized-4bit

8B 8K ctx
Q4_K
4.5GB file 6.63GB
P

P O W E R H A C K

6 models

Qwen2.5-3B-Instruct-Q8_0-GGUF

3B 8K ctx
Q8_0
3.19GB file 5.24GB

Qwen2.5-3B-Q8_0-GGUF

3B 8K ctx
Q8_0
3.19GB file 5.24GB

Qwen2.5-7B-Instruct-1M-Q5_0-GGUF

7B 8K ctx
Q5_0
4.81GB file 6.92GB

Qwen2.5-7B-Instruct-1M-Q8_0-GGUF

7B 8K ctx
Q8_0
7.44GB file 9.55GB

Qwen3-8B-Q5_K_M-GGUF

8B 8K ctx
Q5_0
5.5GB file 7.63GB
FP16
16GB file 18.13GB

Qwen3-8B-Q6_K-GGUF

8B 8K ctx
Q6_0
6.5GB file 8.63GB
FP16
16GB file 18.13GB
P

P0X0

1 models

Astra-v1-12B-GGUF

12B 8K ctx
Q4_0
6.75GB file 8.95GB
Q5_0
8.25GB file 10.45GB
Q6_0
9.75GB file 11.95GB
Q8_0
12.75GB file 14.95GB
P

Pabasara X E

3 models

AceReason-Nemotron-14B-Q3_K_L-GGUF

14B 8K ctx
Q3_0
6.13GB file 8.36GB
FP16
28GB file 30.23GB

AceReason-Nemotron-14B-Q4_K_M-GGUF

14B 8K ctx
Q4_0
7.88GB file 10.11GB
FP16
28GB file 30.23GB

starcoder2-15b-Q4_K_M-GGUF

15B 8K ctx
Q4_0
8.44GB file 10.69GB
FP16
30GB file 32.25GB
P

Pablo Rf

1 models

Llama-3.1-Carballo-Q4_K_M-GGUF

8B 8K ctx
Q4_0
4.5GB file 6.63GB
FP16
16GB file 18.13GB
P

Pablo Sua Lap

1 models

llama-3.1-8b-instruct-reglamentacion-V1-Q4_K_M-GGUF

8B 8K ctx
Q4_0
4.5GB file 6.63GB
FP16
16GB file 18.13GB
P

Pablomo83

1 models

Llama3_credpol

8B 8K ctx
Q4_K_M
4.5GB file 6.63GB
Q8_0
8.5GB file 10.63GB
P

Paddy1703

1 models

tinnyllama-databricks-F16-GGUF

1.1B 8K ctx
FP16
2.2GB file 4.22GB
P

Pahajokiconsulting

2 models

anvil-ward-gate

0.8B 8K ctx
FP16
1.6GB file 3.61GB

anvil-ward-thinker

4B 8K ctx
FP16
8GB file 10.07GB