All Supported Models

29681 AI models · 198875 quantization formats tracked

B

Bullerwins

15 models

DeepSeek-V3-GGUF

3B 8K ctx
Q3_K_M
1.31GB file 3.36GB
Q4_K_M
1.69GB file 3.74GB
Q5_K_M
2.06GB file 4.11GB
Q8_0
3.19GB file 5.24GB
BF16
6GB file 8.05GB

gemma-2-2b-it-GGUF

2B 8K ctx
Q6_K
1.63GB file 3.66GB
Q8_0
2.13GB file 4.16GB
BF16
4GB file 6.03GB

Meta-Llama-3.1-405B-Instruct-GGUF

405B 8K ctx
Q2_K
126.56GB file 135.2GB
Q3_K_L
177.19GB file 185.83GB
Q3_K_M
177.19GB file 185.83GB
Q3_K_S
177.19GB file 185.83GB
Q4_K_M
227.81GB file 236.45GB
Q4_K_S
227.81GB file 236.45GB
Q5_K_M
278.44GB file 287.08GB
Q5_K_S
278.44GB file 287.08GB
Q6_K
329.06GB file 337.7GB

Meta-Llama-3.1-70B-Instruct-GGUF

70B 8K ctx
Q2_K
21.88GB file 25.03GB
Q3_K_L
30.63GB file 33.78GB
Q3_K_M
30.63GB file 33.78GB
Q3_K_S
30.63GB file 33.78GB
Q4_K_M
39.38GB file 42.53GB
Q4_K_S
39.38GB file 42.53GB
Q5_K_M
48.13GB file 51.28GB
Q5_K_S
48.13GB file 51.28GB
Q6_K
56.88GB file 60.03GB
Q8_0
74.38GB file 77.53GB
BF16
140GB file 143.15GB

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

8B 8K ctx
Q2_K
2.5GB file 4.63GB
Q3_K_L
3.5GB file 5.63GB
Q3_K_M
3.5GB file 5.63GB
Q3_K_S
3.5GB file 5.63GB
Q4_K_M
4.5GB file 6.63GB
Q4_K_S
4.5GB file 6.63GB
Q5_K_M
5.5GB file 7.63GB
Q5_K_S
5.5GB file 7.63GB
Q6_K
6.5GB file 8.63GB
Q8_0
8.5GB file 10.63GB
BF16
16GB file 18.13GB

MiniMax-M2-GGUF

2B 8K ctx
Q2_K
0.63GB file 2.66GB
Q3_K_L
0.88GB file 2.91GB
Q3_K_M
0.88GB file 2.91GB
Q3_K_S
0.88GB file 2.91GB
Q4_K_M
1.13GB file 3.16GB
Q4_K_S
1.13GB file 3.16GB
Q5_K_M
1.38GB file 3.41GB
Q5_K_S
1.38GB file 3.41GB
Q6_K
1.63GB file 3.66GB
Q8_0
2.13GB file 4.16GB

MiniMax-M2.1-GGUF

2.1B 8K ctx
Q5_K_M
1.44GB file 3.47GB
Q6_K
1.71GB file 3.74GB
Q8_0
2.23GB file 4.26GB

MiniMax-M2.1-REAP-50-GGUF

50B 8K ctx
Q3_K_L
21.88GB file 24.7GB
Q3_K_M
21.88GB file 24.7GB
Q3_K_S
21.88GB file 24.7GB
Q4_K_M
28.13GB file 30.95GB
Q4_K_S
28.13GB file 30.95GB
Q5_K_M
34.38GB file 37.2GB
Q5_K_S
34.38GB file 37.2GB
Q6_K
40.63GB file 43.45GB
Q8_0
53.13GB file 55.95GB

Qwen2.5-7B-Instruct-GGUF

7B 8K ctx
Q3_K_L
3.06GB file 5.17GB
Q3_K_M
3.06GB file 5.17GB
Q3_K_S
3.06GB file 5.17GB
Q4_K_M
3.94GB file 6.05GB
Q4_K_S
3.94GB file 6.05GB
Q5_K_M
4.81GB file 6.92GB
Q5_K_S
4.81GB file 6.92GB
Q6_K
5.69GB file 7.8GB
Q8_0
7.44GB file 9.55GB

Qwen3-14B-GGUF

14B 8K ctx
Q2_K
4.38GB file 6.61GB
Q3_K_L
6.13GB file 8.36GB
Q3_K_M
6.13GB file 8.36GB
Q3_K_S
6.13GB file 8.36GB
Q4_K_M
7.88GB file 10.11GB
Q4_K_S
7.88GB file 10.11GB
Q5_K_M
9.63GB file 11.86GB
Q5_K_S
9.63GB file 11.86GB
Q6_K
11.38GB file 13.61GB
Q8_0
14.88GB file 17.11GB
BF16
28GB file 30.23GB

Qwen3-30B-A3B-Instruct-2507-GGUF

30B 8K ctx
Q2_K
9.38GB file 11.87GB
Q3_K_L
13.13GB file 15.62GB
Q3_K_M
13.13GB file 15.62GB
Q3_K_S
13.13GB file 15.62GB
Q4_K_M
16.88GB file 19.37GB
Q4_K_S
16.88GB file 19.37GB
Q5_K_M
20.63GB file 23.12GB
Q5_K_S
20.63GB file 23.12GB
Q6_K
24.38GB file 26.87GB
Q8_0
31.88GB file 34.37GB
BF16
60GB file 62.49GB

Qwen3-4B-Instruct-2507-GGUF

4B 8K ctx
Q2_K
1.25GB file 3.32GB
Q3_K_L
1.75GB file 3.82GB
Q3_K_M
1.75GB file 3.82GB
Q3_K_S
1.75GB file 3.82GB
Q4_K_M
2.25GB file 4.32GB
Q4_K_S
2.25GB file 4.32GB
Q5_K_M
2.75GB file 4.82GB
Q5_K_S
2.75GB file 4.82GB
Q6_K
3.25GB file 5.32GB
Q8_0
4.25GB file 6.32GB
BF16
8GB file 10.07GB

Qwen3-8B-GGUF

8B 8K ctx
Q2_K
2.5GB file 4.63GB
Q3_K_L
3.5GB file 5.63GB
Q3_K_M
3.5GB file 5.63GB
Q3_K_S
3.5GB file 5.63GB
Q4_K_M
4.5GB file 6.63GB
Q4_K_S
4.5GB file 6.63GB
Q5_K_M
5.5GB file 7.63GB
Q5_K_S
5.5GB file 7.63GB
Q6_K
6.5GB file 8.63GB
Q8_0
8.5GB file 10.63GB
BF16
16GB file 18.13GB

Qwen3-Coder-30B-A3B-Instruct-GGUF

30B 8K ctx
Q4_K_M
16.88GB file 19.37GB
Q4_K_S
16.88GB file 19.37GB
Q5_K_M
20.63GB file 23.12GB
Q5_K_S
20.63GB file 23.12GB
Q6_K
24.38GB file 26.87GB
Q8_0
31.88GB file 34.37GB
BF16
60GB file 62.49GB

Reflection-Llama-3.1-70B-GGUF

70B 8K ctx
Q2_K
21.88GB file 25.03GB
Q3_K_L
30.63GB file 33.78GB
Q3_K_M
30.63GB file 33.78GB
Q3_K_S
30.63GB file 33.78GB
Q4_K_M
39.38GB file 42.53GB
Q4_K_S
39.38GB file 42.53GB
Q5_K_M
48.13GB file 51.28GB
Q5_K_S
48.13GB file 51.28GB
Q6_K
56.88GB file 60.03GB
Q8_0
74.38GB file 77.53GB
B

Bumoch

2 models

The_Creeping_Darkness-X2-16B

16B 8K ctx
FP16
32GB file 34.26GB

The_Darkside-16.6B

12B 8K ctx
FP16
24GB file 26.2GB
B

Bunny0417

2 models

llama-3.2-1bFour-Wheeler

1B 8K ctx
FP16
2GB file 4.02GB

llama-3.2-1bTwo-Wheeler

1B 8K ctx
FP16
2GB file 4.02GB
B

Burrowswang

1 models

Qwen3Guard-Gen-4B-Q4_K_M-GGUF

4B 8K ctx
Q4_0
2.25GB file 4.32GB
FP16
8GB file 10.07GB
B

Burtenshaw

1 models

gemma-help-tiny-sft

2B 8K ctx
Q8_0
2.13GB file 4.16GB
B

Bus Rune

1 models

L3.1-8B-Fabula-Q8_0-GGUF

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

Busratuter

1 models

metal-rock

Unknown 8K ctx
Q4_K_M
0GB file 2GB
B

Buuhzerah

1 models

gemma-code-2b-instruct-finetune-test

2B 8K ctx
FP16
4GB file 6.03GB
B

Buyy

1 models

ontomind-qwen-14b

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

Bveiseh

1 models

phi4-magpie-reasoning-v4-gguf

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