All Supported Models

29681 AI models · 198875 quantization formats tracked

V

Vdumanov

1 models

Llama-3.1-Minitron-4B-Chat-Q6_K-GGUF

4B 8K ctx
Q6_0
3.25GB file 5.32GB
FP16
8GB file 10.07GB
V

Vectorventures

1 models

Llama-3-8b-64k-PoSE-Q6_K-GGUF

8B 8K ctx
Q6_K
6.5GB file 8.63GB
V

Vegeta03

1 models

Qwen2.5-Coder-7B-Q8_0-GGUF

7B 8K ctx
Q8_0
7.44GB file 9.55GB
V

Velyan

11 models

Llama-3.2-1B-Instruct-IQ3_M-GGUF

1B 8K ctx
Q3_0
0.44GB file 2.46GB
FP16
2GB file 4.02GB

Llama-3.2-1B-Instruct-Q5_K_M-GGUF

1B 8K ctx
Q5_0
0.69GB file 2.71GB
FP16
2GB file 4.02GB

Llama-3.2-1B-Instruct-Q8_0-GGUF

1B 8K ctx
Q8_0
1.06GB file 3.08GB

Llama-3.2-1B-Q2_K-GGUF

1B 8K ctx
Q2_0
0.31GB file 2.33GB
FP16
2GB file 4.02GB

Llama-3.2-3B-Instruct-IQ3_M-GGUF

3B 8K ctx
Q3_0
1.31GB file 3.36GB
FP16
6GB file 8.05GB

Llama-3.2-3B-Instruct-IQ3_XXS-GGUF

3B 8K ctx
Q3_0
1.31GB file 3.36GB
FP16
6GB file 8.05GB

Llama-3.2-3B-Instruct-Q3_K_L-GGUF

3B 8K ctx
Q3_0
1.31GB file 3.36GB
Q4_0
1.69GB file 3.74GB
Q5_0
2.06GB file 4.11GB
FP16
6GB file 8.05GB

Llama-3.2-3B-Instruct-Q3_K_M-GGUF

3B 8K ctx
Q3_0
1.31GB file 3.36GB
FP16
6GB file 8.05GB

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

3B 8K ctx
Q3_0
1.31GB file 3.36GB
Q4_0
1.69GB file 3.74GB
Q5_0
2.06GB file 4.11GB
FP16
6GB file 8.05GB

Llama-3.2-3B-Instruct-Q5_0-GGUF

3B 8K ctx
Q5_0
2.06GB file 4.11GB

Llama-3.2-3B-Instruct-Q5_K_S-GGUF

3B 8K ctx
Q5_0
2.06GB file 4.11GB
FP16
6GB file 8.05GB
V

Vemas

2 models

Dolphin-Mistral-24B-Venice-Edition-Q4_K_M-GGUF

24B 8K ctx
Q4_0
13.5GB file 15.89GB
FP16
48GB file 50.39GB

SmolLCoder-360M-Instruct-Q8_0-GGUF

0B 8K ctx
Q8_0
0GB file 2GB
V

Vencibo

2 models

BgGPT-7B-Instruct-v0.2-Q5_K_M-GGUF

7B 8K ctx
Q5_0
4.81GB file 6.92GB
FP16
14GB file 16.11GB

gemma-2-2b-Q5_K_M-GGUF

2B 8K ctx
Q5_0
1.38GB file 3.41GB
FP16
4GB file 6.03GB
V

Venkat9990

1 models

finance-specialist-v7

1B 8K ctx
Q4_K_M
0.56GB file 2.58GB
V

Venkatsriram

1 models

Llama-Guard-3-8B-Q4_K_M-GGUF

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

Verdugie

18 models

Opus-Candid-14B-V1

14B 8K ctx
Q6_K
11.38GB file 13.61GB
Q8_0
14.88GB file 17.11GB

Opus-Candid-27B-V2.1

27B 8K ctx
Q4_K_M
15.19GB file 17.63GB
Q6_K
21.94GB file 24.38GB
Q8_0
28.69GB file 31.13GB

Opus-Candid-27B-V3

27B 8K ctx
Q4_K_M
15.19GB file 17.63GB
Q6_K
21.94GB file 24.38GB
Q8_0
28.69GB file 31.13GB

Opus-Candid-27B-V3.5

27B 8K ctx
Q4_K_M
15.19GB file 17.63GB
Q6_K
21.94GB file 24.38GB
Q8_0
28.69GB file 31.13GB

Opus-Candid-32B-V1

32B 8K ctx
Q4_K_M
18GB file 20.52GB
Q8_0
34GB file 36.52GB

Opus-Candid-70B-V1

72B 8K ctx
Q4_K_M
40.5GB file 43.68GB
Q8_0
76.5GB file 79.68GB

Opus-Candid-8B-V1

7B 8K ctx
Q8_0
7.44GB file 9.55GB

Opus-Candid-8B-V2

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

Opus-Candid-8B-V2.1

8B 8K ctx
Q8_0
8.5GB file 10.63GB

Opus-Candid-8B-V3

8B 8K ctx
Q6_K
6.5GB file 8.63GB
Q8_0
8.5GB file 10.63GB

Opus-Candid-Lite-4B

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB
Q6_K
3.25GB file 5.32GB
Q8_0
4.25GB file 6.32GB

Opus-Candid-Lite-4B-K

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB
Q6_K
3.25GB file 5.32GB
Q8_0
4.25GB file 6.32GB

Opus-Candid-Lite-4B-P

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB
Q6_K
3.25GB file 5.32GB
Q8_0
4.25GB file 6.32GB

Opus-Candid-MoE-V2

Unknown 8K ctx
Q4_K_M
0GB file 2GB
Q8_0
0GB file 2GB

Opus-Candid-MoE-V3

30B 8K ctx
Q4_K_M
16.88GB file 19.37GB
Q6_K
24.38GB file 26.87GB
Q8_0
31.88GB file 34.37GB

Opus-MCP-Research-v0.5

Unknown 8K ctx
Q6_K
0GB file 2GB
Q4_K_M
0GB file 2GB
BF16
0GB file 2GB
Q8_0
0GB file 2GB

Opus-Research-8B-V1.5

7B 8K ctx
Q8_0
7.44GB file 9.55GB

STEM-Oracle-27B

27B 8K ctx
Q4_K_M
15.19GB file 17.63GB
Q6_K
21.94GB file 24.38GB
Q8_0
28.69GB file 31.13GB
BF16
54GB file 56.44GB
V

Verknipte

1 models

XortronCriminalComputingConfig-Q4_K_M-GGUF

Unknown 8K ctx
Q4_0
0GB file 2GB
FP16
0GB file 2GB