Gemma is a family of lightweight, state-of-the-art open models built by Google DeepMind. Updated to version 1.1
1.4M Pulls Updated 5 weeks ago
instruct
5.0GB
text
5.2GB
v1.1
5.0GB
7b-instruct
5.0GB
7b-text
5.2GB
7b-v1.1
5.0GB
7b-instruct-q4_0
5.2GB
7b-instruct-q4_1
5.7GB
7b-instruct-q5_0
6.2GB
7b-instruct-q5_1
6.7GB
7b-instruct-q8_0
9.1GB
7b-instruct-q2_K
3.7GB
7b-instruct-q3_K_S
4.2GB
7b-instruct-q3_K_M
4.6GB
7b-instruct-q3_K_L
4.9GB
7b-instruct-q4_K_S
5.2GB
7b-instruct-q4_K_M
5.5GB
7b-instruct-q5_K_S
6.2GB
7b-instruct-q5_K_M
6.3GB
7b-instruct-q6_K
7.2GB
7b-instruct-fp16
17GB
7b-text-q4_0
5.2GB
7b-text-q4_1
5.7GB
7b-text-q5_0
6.2GB
7b-text-q5_1
6.7GB
7b-text-q8_0
9.1GB
7b-text-q2_K
3.7GB
7b-text-q3_K_S
4.2GB
7b-text-q3_K_M
4.6GB
7b-text-q3_K_L
4.9GB
7b-text-q4_K_S
5.2GB
7b-text-q4_K_M
5.5GB
7b-text-q5_K_S
6.2GB
7b-text-q5_K_M
6.3GB
7b-text-q6_K
7.2GB
7b-text-fp16
16GB
7b-instruct-v1.1-q4_0
5.0GB
7b-instruct-v1.1-q4_1
5.5GB
7b-instruct-v1.1-q5_0
6.0GB
7b-instruct-v1.1-q5_1
6.5GB
7b-instruct-v1.1-q8_0
9.1GB
7b-instruct-v1.1-q2_K
3.5GB
7b-instruct-v1.1-q3_K_S
4.0GB
7b-instruct-v1.1-q3_K_M
4.4GB
7b-instruct-v1.1-q3_K_L
4.7GB
7b-instruct-v1.1-q4_K_S
5.0GB
7b-instruct-v1.1-q4_K_M
5.3GB
7b-instruct-v1.1-q5_K_S
6.0GB
7b-instruct-v1.1-q5_K_M
6.1GB
7b-instruct-v1.1-q6_K
7.0GB
7b-instruct-v1.1-fp16
17GB
2b-instruct
1.6GB
2b-text
1.7GB
2b-v1.1
1.6GB
2b-instruct-q4_0
1.7GB
2b-instruct-q4_1
1.8GB
2b-instruct-q5_0
1.9GB
2b-instruct-q5_1
2.1GB
2b-instruct-q8_0
2.7GB
2b-instruct-q2_K
1.3GB
2b-instruct-q3_K_S
1.4GB
2b-instruct-q3_K_M
1.5GB
2b-instruct-q3_K_L
1.6GB
2b-instruct-q4_K_S
1.7GB
2b-instruct-q4_K_M
1.8GB
2b-instruct-q5_K_S
1.9GB
2b-instruct-q5_K_M
2.0GB
2b-instruct-q6_K
2.2GB
2b-instruct-fp16
4.5GB
2b-text-q4_0
1.7GB
2b-text-q4_1
1.8GB
2b-text-q5_0
1.9GB
2b-text-q5_1
2.1GB
2b-text-q8_0
2.7GB
2b-text-q2_K
1.3GB
2b-text-q3_K_S
1.4GB
2b-text-q3_K_M
1.5GB
2b-text-q3_K_L
1.6GB
2b-text-q4_K_S
1.7GB
2b-text-q4_K_M
1.8GB
2b-text-q5_K_S
1.9GB
2b-text-q5_K_M
2.0GB
2b-text-q6_K
2.2GB
2b-text-fp16
4.5GB
2b-instruct-v1.1-q4_0
1.6GB
2b-instruct-v1.1-q4_1
1.7GB
2b-instruct-v1.1-q5_0
1.8GB
2b-instruct-v1.1-q5_1
1.9GB
2b-instruct-v1.1-q8_0
2.7GB
2b-instruct-v1.1-q2_K
1.2GB
2b-instruct-v1.1-q3_K_S
1.3GB
2b-instruct-v1.1-q3_K_M
1.4GB
2b-instruct-v1.1-q3_K_L
1.5GB
2b-instruct-v1.1-q4_K_S
1.6GB
2b-instruct-v1.1-q4_K_M
1.6GB
2b-instruct-v1.1-q5_K_S
1.8GB
2b-instruct-v1.1-q5_K_M
1.8GB
2b-instruct-v1.1-q6_K
2.1GB
2b-instruct-v1.1-fp16
5.0GB