mistral-nemo

A state-of-the-art 12B model with 128k context length, built by Mistral AI in collaboration with NVIDIA.

Tools 12B

167.1K Pulls Updated 5 weeks ago

17 Tags

994f3b8b7801 • 7.1GB • Updated 5 weeks ago

latest

994f3b8b7801 • 7.1GB • Updated 5 weeks ago

12b-instruct-2407-fp16

7bb1e26a5ed5 • 25GB • Updated 5 weeks ago

12b-instruct-2407-q2_K

afa0d9b8759f • 4.8GB • Updated 5 weeks ago

12b-instruct-2407-q3_K_S

864043847fc7 • 5.5GB • Updated 5 weeks ago

12b-instruct-2407-q3_K_M

09c8706f02f4 • 6.1GB • Updated 5 weeks ago

12b-instruct-2407-q3_K_L

affbdc0a347a • 6.6GB • Updated 5 weeks ago

12b-instruct-2407-q4_0

994f3b8b7801 • 7.1GB • Updated 5 weeks ago

12b-instruct-2407-q4_1

2b87a40ca999 • 7.8GB • Updated 5 weeks ago

12b-instruct-2407-q4_K_S

2c2b8e074f09 • 7.1GB • Updated 5 weeks ago

12b-instruct-2407-q4_K_M

1da0ebbdb7ca • 7.5GB • Updated 5 weeks ago

12b-instruct-2407-q5_0

0fc0a9ed80c9 • 8.5GB • Updated 5 weeks ago

12b-instruct-2407-q5_1

f811366ff2b3 • 9.2GB • Updated 5 weeks ago

12b-instruct-2407-q5_K_S

5fc038ec8027 • 8.5GB • Updated 5 weeks ago

12b-instruct-2407-q5_K_M

d0e3d91c3c3e • 8.7GB • Updated 5 weeks ago

12b-instruct-2407-q6_K

7a5dbe4123f4 • 10GB • Updated 5 weeks ago

12b-instruct-2407-q8_0

b91eec34730f • 13GB • Updated 5 weeks ago