All Supported Models

29681 AI models · 198875 quantization formats tracked

S

Sultan R

2 models

SmolTulu-1.7b-Instruct-GGUF

1.7B 8K ctx
Q4_0
0.96GB file 2.99GB
FP16
3.4GB file 5.43GB

SmolTulu-1.7b-Reinforced-GGUF

1.7B 8K ctx
Q4_K_M
0.96GB file 2.99GB
S

Sultanali338

1 models

qwen1.5-1.8b-gguf

1.8B 8K ctx
Q4_K_M
1.01GB file 3.04GB
Q5_K_M
1.24GB file 3.27GB
S

Sumail

7 models

Meta-Llama-3.1-8B-Instruct-Q2_K-GGUF

8B 8K ctx
Q2_0
2.5GB file 4.63GB
FP16
16GB file 18.13GB

Meta-Llama-3.1-8B-Instruct-Q3_K_M-GGUF

8B 8K ctx
Q3_0
3.5GB file 5.63GB
FP16
16GB file 18.13GB

Meta-Llama-3.1-8B-Instruct-Q3_K_S-GGUF

8B 8K ctx
Q3_0
3.5GB file 5.63GB
FP16
16GB file 18.13GB

Meta-Llama-3.1-8B-Instruct-Q5_0-GGUF

8B 8K ctx
Q5_0
5.5GB file 7.63GB

Meta-Llama-3.1-8B-Instruct-Q5_K_M-GGUF

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

Meta-Llama-3.1-8B-Instruct-Q6_K-GGUF

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

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

8B 8K ctx
Q8_0
8.5GB file 10.63GB
S

Sumeyya

1 models

llama-3-8b-chat-doctor

8B 8K ctx
Q4_K_M
4.5GB file 6.63GB
S

Sumgai

7 models

Mistral-Devstral-2505-CODER-Brainstorm40x-44B-Q8_0-GGUF

44B 8K ctx
Q8_0
46.75GB file 49.47GB

Mistral-Devstral-2507-CODER-Brainstorm40x-44B-Q8_0-GGUF

44B 8K ctx
Q8_0
46.75GB file 49.47GB

Mistral-Magistral-Devstral-Instruct-FUSED-CODER-Reasoning-36B-Q5_K_S-GGUF

36B 8K ctx
Q5_0
24.75GB file 27.34GB
FP16
72GB file 74.59GB

Mistral-Magistral-Devstral-Instruct-FUSED-CODER-Reasoning-36B-Q8_0-GGUF

36B 8K ctx
Q8_0
38.25GB file 40.84GB

openbuddy-codellama2-34b-v11.1-bf16-Q8_0-GGUF

34B 8K ctx
Q8_0
36.13GB file 38.69GB

Qwen3-42B-A3B-2507-Thinking-Abliterated-uncensored-TOTAL-RECALL-v2-Medium-MASTER-CODER-Q8_0-GGUF

42B 8K ctx
Q8_0
44.63GB file 47.32GB

Qwen3-42B-A3B-2507-TOTAL-RECALL-v2-Medium-MASTER-CODER-Q8_0-GGUF

42B 8K ctx
Q8_0
44.63GB file 47.32GB
S

Suminimini

5 models

EXAONE-4.0-1.2B-Q4_K_M-GGUF

1.2B 8K ctx
Q4_0
0.67GB file 2.69GB
FP16
2.4GB file 4.42GB

EXAONE-4.0-1.2B-Q6_K-GGUF

1.2B 8K ctx
Q6_0
0.98GB file 3GB
FP16
2.4GB file 4.42GB

EXAONE-4.0-1.2B-Q8_0-GGUF

1.2B 8K ctx
Q8_0
1.28GB file 3.3GB

EXAONE-4.0-32B-Q4_K_M-GGUF

32B 8K ctx
Q4_0
18GB file 20.52GB
FP16
64GB file 66.52GB

KONI-Llama3.1-8B-Instruct-20241024-Q4_K_M-GGUF

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

Summit4You

1 models

Llama3-8B-COIG-CQIA-GGUF

8B 8K ctx
Q8_0
8.5GB file 10.63GB
S

Sunbird

2 models

Sunflower-14B-GGUF

14B 8K ctx
Q2_0
4.38GB file 6.61GB
Q4_0
7.88GB file 10.11GB
Q5_0
9.63GB file 11.86GB
Q6_0
11.38GB file 13.61GB
Q1_0
14GB file 16.23GB
Q8_0
14.88GB file 17.11GB

Sunflower-32B-GGUF

32B 8K ctx
Q2_0
10GB file 12.52GB
Q4_0
18GB file 20.52GB
Q5_0
22GB file 24.52GB
Q6_0
26GB file 28.52GB
Q1_0
32GB file 34.52GB
Q8_0
34GB file 36.52GB
S

Sunil Pathak

20 models

gemma-3n-E2B-it-IQ4_NL

2B 8K ctx
Q4_NL
1.13GB file 3.16GB

gemma-3n-E2B-it-Q4_K_M

2B 8K ctx
Q4_K_M
1.13GB file 3.16GB

gemma-3n-E2B-it-Q5_K_M

2B 8K ctx
Q5_K_M
1.38GB file 3.41GB

gemma-3n-E2B-it-Q6_K

2B 8K ctx
Q6_K
1.63GB file 3.66GB

gemma-4-E2B-it-IQ4_NL

2B 8K ctx
Q4_NL
1.13GB file 3.16GB

gemma-4-E2B-it-Q4_K_M

2B 8K ctx
Q4_K_M
1.13GB file 3.16GB

gemma-4-E2B-it-Q5_K_M

2B 8K ctx
Q5_K_M
1.38GB file 3.41GB

gemma-4-E2B-it-Q6_K

2B 8K ctx
Q6_K
1.63GB file 3.66GB

gemma-4-E4B-it-GGUF

4B 8K ctx
Q8_0
4.25GB file 6.32GB
FP16
8GB file 10.07GB

gemma-4-E4B-it-IQ4_NL

4B 8K ctx
Q4_NL
2.25GB file 4.32GB

gemma-4-E4B-it-Q4_K_M

4B 8K ctx
Q4_K_M
2.25GB file 4.32GB

gemma-4-E4B-it-Q5_K_M

4B 8K ctx
Q5_K_M
2.75GB file 4.82GB

gemma-4-E4B-it-Q6_K

4B 8K ctx
Q6_K
3.25GB file 5.32GB

Mistral-7B-Instruct-v0.3-IQ4_NL

7B 8K ctx
Q4_NL
3.94GB file 6.05GB

Mistral-7B-Instruct-v0.3-Q4_K_M

7B 8K ctx
Q4_K_M
3.94GB file 6.05GB

Mistral-7B-Instruct-v0.3-Q5_K_M

7B 8K ctx
Q5_K_M
4.81GB file 6.92GB

Mistral-7B-Instruct-v0.3-Q6_K

7B 8K ctx
Q6_K
5.69GB file 7.8GB

Qwen3.5-9B-IQ4_NL

9B 8K ctx
Q4_NL
5.06GB file 7.21GB

Qwen3.5-9B-Q5_K_M

9B 8K ctx
Q5_K_M
6.19GB file 8.34GB

Qwen3.5-9B-Q6_K

9B 8K ctx
Q6_K
7.31GB file 9.46GB
S

Sunkencity

2 models

Llama-3.1-8B-Blasphemer-GGUF

8B 8K ctx
Q4_K_M
4.5GB file 6.63GB
Q5_K_M
5.5GB file 7.63GB

xLAM-GGUF

8B 8K ctx
Q4_K_M
4.5GB file 6.63GB
Q6_K
6.5GB file 8.63GB
Q8_0
8.5GB file 10.63GB