All Supported Models

29681 AI models · 198875 quantization formats tracked

N

Nateca

1 models

kanana-1.5-2.1b-instruct-2505-Q4_K_M-GGUF

2.1B 8K ctx
Q4_0
1.18GB file 3.21GB
FP16
4.2GB file 6.23GB
N

Nathan Assis

1 models

Llama-3.2-3B-Instruct-Q4_K_M-GGUF

3B 8K ctx
Q4_0
1.69GB file 3.74GB
FP16
6GB file 8.05GB
N

Nativemind

1 models

sphere_047_m4_overnight-gguf

1.1B 8K ctx
Q4_0
0.62GB file 2.64GB
Q5_0
0.76GB file 2.78GB
Q8_0
1.17GB file 3.19GB
N

Nautilie7

11 models

AMD-OLMo-1B-SFT-Q8_0-GGUF

1B 8K ctx
Q8_0
1.06GB file 3.08GB

gemma-2-2b-it-Q8_0-GGUF

2B 8K ctx
Q8_0
2.13GB file 4.16GB

gemma-2-2b-Q8_0-GGUF

2B 8K ctx
Q8_0
2.13GB file 4.16GB

Llama-3.1-8B-Instruct-Q8_0-GGUF

8B 8K ctx
Q8_0
8.5GB file 10.63GB

Llama-3.2-1B-Instruct-IQ4_NL-GGUF

1B 8K ctx
Q4_0
0.56GB file 2.58GB
FP16
2GB file 4.02GB

OpenCoder-1.5B-Instruct-Q8_0-GGUF

1.5B 8K ctx
Q8_0
1.59GB file 3.61GB

OpenCoder-8B-Instruct-Q8_0-GGUF

8B 8K ctx
Q8_0
8.5GB file 10.63GB

Phi-3.5-mini-instruct-Q5_K_S-GGUF

3.8B 8K ctx
Q5_0
2.61GB file 4.67GB
FP16
7.6GB file 9.66GB

Phi-3.5-mini-instruct-Q8_0-GGUF

0B 8K ctx
Q8_0
0GB file 2GB

Qwen2.5-Coder-1.5B-Instruct-Q8_0-GGUF

1.5B 8K ctx
Q8_0
1.59GB file 3.61GB

Qwen2.5-Coder-1.5B-Q8_0-GGUF

1.5B 8K ctx
Q8_0
1.59GB file 3.61GB
N

Navanchauhan

1 models

Huihui-Qwopus3.5-9B-v3-abliterated-TQ3_4S

9B 8K ctx
Q3_4S
3.94GB file 6.09GB
N

Navicore

1 models

fortean-qwen3-8b-advanced-GGUF

3B 8K ctx
Q4_0
1.69GB file 3.74GB
FP16
6GB file 8.05GB
N

Navpy

1 models

phi-3.5-AI-Vtuber-json

3.8B 8K ctx
Q4_K_M
2.14GB file 4.2GB
N

Nawazadroit

1 models

llama3.2Q4

1B 8K ctx
Q4_0
0.56GB file 2.58GB
FP16
2GB file 4.02GB
N

Nayyt

3 models

Lamarck-14B-v0.7-Q4_K_M-GGUF

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

Lamarck-14B-v0.7-Q8_0-GGUF

14B 8K ctx
Q8_0
14.88GB file 17.11GB

ultiima-32B-Q5_K_M-GGUF

32B 8K ctx
Q5_0
22GB file 24.52GB
FP16
64GB file 66.52GB
N

Nazimali

2 models

mistral-7b-v0.3-instruct-arabic

7B 8K ctx
Q4_K_M
3.94GB file 6.05GB
Q6_K
5.69GB file 7.8GB
Q8_0
7.44GB file 9.55GB

Mistral-Nemo-Kurdish-Instruct

12B 8K ctx
Q4_K_M
6.75GB file 8.95GB
Q6_K
9.75GB file 11.95GB
BF16
24GB file 26.2GB