All Supported Models

29681 AI models · 198875 quantization formats tracked

A

Alibaba Cloud

4 models

Qwen2.5 72B

72B 131K ctx
★ Popular
Q3_K_M
31.6GB file 56.6GB
Q4_K_M
43GB file 68GB
Q8_0
77.7GB file 102.7GB

Qwen2.5 7B

7B 131K ctx
★ Popular
Q4_K_M
4.36GB file 8.5GB
Q8_0
7.98GB file 12.1GB
FP16
15.65GB file 19.8GB

Qwen3 32B

32B 131K ctx
Q4_K_M
19.85GB file 31.5GB
Q8_0
34.35GB file 46GB

Qwen3 8B

8B 131K ctx
★ Popular
Q4_K_M
4.94GB file 9.1GB
Q8_0
8.99GB file 13.2GB
FP16
16.59GB file 20.7GB
G

Google DeepMind

4 models

Gemma 2 27B

27B 8K ctx
★ Popular
Q4_K_M
15.64GB file 18.1GB
Q6_K
20.31GB file 22.8GB
Q8_0
28.97GB file 31.4GB

Gemma 2 2B

2B 8K ctx
Q4_K_M
1.63GB file 3.7GB
Q8_0
2.67GB file 4.7GB
FP16
5.24GB file 7.3GB

Gemma 2 9B

9B 8K ctx
★ Popular
Q4_K_M
5.44GB file 7.6GB
Q6_K
7.06GB file 9.2GB
Q8_0
9.83GB file 12GB
FP16
18.49GB file 20.6GB

Gemma 3 12B

12B 131K ctx
★ Popular
Q4_K_M
7.27GB file 12.4GB
Q8_0
12.98GB file 18.2GB
FP16
24.44GB file 29.6GB
M

Meta AI

5 models

Llama 3.1 405B

405B 131K ctx
Q4_K_M
229GB file 338.5GB
FP8
404GB file 511.2GB

Llama 3.1 70B

70B 131K ctx
★ Popular
Q3_K_M
29GB file 48.4GB
Q4_K_M
39GB file 58.1GB
Q5_K_M
48GB file 67.2GB
Q8_0
74GB file 93.2GB

Llama 3.1 8B

8B 131K ctx
★ Popular
Q3_K_M
3.3GB file 7.4GB
Q4_K_M
4.58GB file 8.7GB
Q5_K_M
5.33GB file 9.4GB
Q6_K
6.14GB file 10.3GB
Q8_0
8.54GB file 12.7GB
FP16
16.07GB file 20.1GB

Llama 3.2 3B

3B 131K ctx
Q4_K_M
1.89GB file 4.7GB
Q6_K
2.46GB file 5.3GB
Q8_0
3.42GB file 6.2GB
FP16
6.43GB file 9.2GB

Llama 3.3 70B

70B 131K ctx
★ Popular
Q4_K_M
39GB file 58.1GB
Q5_K_M
48GB file 67.2GB
Q8_0
74GB file 93.2GB
D

DeepSeek

3 models

DeepSeek R1 70B

70B 131K ctx
★ Popular
Q4_K_M
39.2GB file 58.3GB
Q5_K_M
48GB file 67.1GB

DeepSeek R1 7B

7B 131K ctx
★ Popular
Q4_K_M
4.36GB file 8.5GB
Q8_0
7.95GB file 12.1GB
FP16
14.96GB file 19.1GB

DeepSeek V3 671B

671B 131K ctx
Q4_K_M
376GB file 554GB
M

Microsoft

5 models

bitnet-b1.58-2B-4T-gguf

2B 8K ctx
FP16
4GB file 6.03GB

Phi-3-mini-4k-instruct-gguf

3.8B 8K ctx
Q4_0
2.14GB file 4.2GB
FP16
7.6GB file 9.66GB

Phi-3.5 Mini 3.8B

3.8B 131K ctx
★ Popular
Q4_K_M
2.39GB file 6.4GB
Q8_0
4.06GB file 8.1GB
FP16
7.64GB file 11.6GB

Phi-4 14B

14B 16K ctx
★ Popular
Q4_K_M
8.49GB file 11GB
Q8_0
15.58GB file 18GB
FP16
29.5GB file 32GB

phi-4-gguf

4B 8K ctx
Q2_K
1.25GB file 3.32GB
Q2_0
1.25GB file 3.32GB
Q3_K
1.75GB file 3.82GB
Q3_K_L
1.75GB file 3.82GB
Q3_K_S
1.75GB file 3.82GB
Q3_M
1.75GB file 3.82GB
Q3_S
1.75GB file 3.82GB
Q3_XS
1.75GB file 3.82GB
Q3_XXS
1.75GB file 3.82GB
Q4_NL
2.25GB file 4.32GB
Q4_0
2.25GB file 4.32GB
Q4_1
2.25GB file 4.32GB
Q4_K
2.25GB file 4.32GB
Q4_K_S
2.25GB file 4.32GB
Q4_XS
2.25GB file 4.32GB
Q5_0
2.75GB file 4.82GB
Q5_1
2.75GB file 4.82GB
Q5_K
2.75GB file 4.82GB
Q5_K_S
2.75GB file 4.82GB
Q6_K
3.25GB file 5.32GB
Q1_0
4GB file 6.07GB
Q8_0
4.25GB file 6.32GB
BF16
8GB file 10.07GB
M

Mistral AI

3 models

Mistral 7B v0.3

7B 33K ctx
★ Popular
Q4_K_M
4.07GB file 6.5GB
Q5_K_M
4.78GB file 7.2GB
Q8_0
7.7GB file 10.2GB
FP16
14.48GB file 17GB

Mistral Nemo 12B

12B 131K ctx
Q4_K_M
7.07GB file 12.3GB
Q8_0
12.83GB file 18GB
FP16
24.5GB file 29.7GB

Mixtral 8x7B

56B 33K ctx
★ Popular
Q3_K_M
19.8GB file 24.4GB
Q4_K_M
26.4GB file 31GB
Q5_K_M
32.1GB file 36.7GB
Q8_0
47.1GB file 51.7GB
0

08210821Iy

1 models

Qwen3-4B-Coder

4B 8K ctx
Q4_0
2.25GB file 4.32GB
FP16
8GB file 10.07GB
0

0Arch Io

1 models

dolphin-v2-8b-abliterated

8B 8K ctx
Q4_K_M
4.5GB file 6.63GB
Q8_0
8.5GB file 10.63GB
0

0Gites

1 models

PLLuM-12B-chat-2512-Q6_K-GGUF

12B 8K ctx
Q6_0
9.75GB file 11.95GB
FP16
24GB file 26.2GB
0

0Sz1

1 models

IT-Auditor-8B-PRO

8B 8K ctx
Q8_0
8.5GB file 10.63GB
FP16
16GB file 18.13GB