granite3.1-moe

The IBM Granite 1B and 3B models are long-context mixture of experts (MoE) Granite models from IBM designed for low latency usage.

tools 1b 3b

10.9K 8 hours ago

33 Tags
latest
b43d80d7fca7 • 2.0GB • 9 hours ago
1b
3269ce3e31ea • 1.4GB • 4 weeks ago
3b
b43d80d7fca7 • 2.0GB • 9 hours ago
1b-instruct-fp16
99904f51aa5c • 2.7GB • 4 weeks ago
1b-instruct-q2_K
6521a8fa2f7d • 524MB • 9 hours ago
1b-instruct-q3_K_L
38e819bae7cb • 724MB • 9 hours ago
1b-instruct-q3_K_M
a9921af691fb • 671MB • 9 hours ago
1b-instruct-q3_K_S
c81277fe1196 • 610MB • 9 hours ago
1b-instruct-q4_0
f1e180ae50b0 • 781MB • 9 hours ago
1b-instruct-q4_1
d62c69d05bc9 • 861MB • 9 hours ago
1b-instruct-q4_K_M
f825ee9e296f • 834MB • 9 hours ago
1b-instruct-q4_K_S
531849afb99e • 787MB • 9 hours ago
1b-instruct-q5_0
3d8012283ac9 • 941MB • 9 hours ago
1b-instruct-q5_1
39b91d40cf9e • 1.0GB • 9 hours ago
1b-instruct-q5_K_M
6c0ad5f8dbc5 • 969MB • 9 hours ago
1b-instruct-q5_K_S
fcc3d042cf51 • 941MB • 9 hours ago
1b-instruct-q6_K
72cde855354e • 1.1GB • 9 hours ago
1b-instruct-q8_0
3269ce3e31ea • 1.4GB • 4 weeks ago
3b-instruct-fp16
cdedb7e7b102 • 6.6GB • 4 weeks ago
3b-instruct-q2_K
7ea974a9d11f • 1.3GB • 9 hours ago
3b-instruct-q3_K_L
712573071d24 • 1.8GB • 9 hours ago
3b-instruct-q3_K_M
216dcd8f0222 • 1.6GB • 9 hours ago
3b-instruct-q3_K_S
86de476c2ed2 • 1.5GB • 9 hours ago
3b-instruct-q4_0
575c94ea9f74 • 1.9GB • 9 hours ago
3b-instruct-q4_1
a4c8618969bb • 2.1GB • 9 hours ago
3b-instruct-q4_K_M
b43d80d7fca7 • 2.0GB • 9 hours ago
3b-instruct-q4_K_S
71da5b32c299 • 1.9GB • 9 hours ago
3b-instruct-q5_0
ac1c3501f148 • 2.3GB • 8 hours ago
3b-instruct-q5_1
14ba2faee6e3 • 2.5GB • 8 hours ago
3b-instruct-q5_K_M
fac03e34e804 • 2.4GB • 8 hours ago
3b-instruct-q5_K_S
ec25600ae9c5 • 2.3GB • 8 hours ago
3b-instruct-q6_K
b49c14c5cac4 • 2.7GB • 8 hours ago
3b-instruct-q8_0
038f46903bbd • 3.5GB • 4 weeks ago