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

1,925 4 days ago

33 Tags
latest
df6f6578dba8 • 2.0GB • 4 days ago
1b
3269ce3e31ea • 1.4GB • 4 days ago
3b
df6f6578dba8 • 2.0GB • 4 days ago
1b-instruct-fp16
99904f51aa5c • 2.7GB • 4 days ago
1b-instruct-q2_K
b9cc1d12c566 • 512MB • 4 days ago
1b-instruct-q3_K_L
42c379410ea3 • 711MB • 4 days ago
1b-instruct-q3_K_M
d5192f2d5ded • 659MB • 4 days ago
1b-instruct-q3_K_S
a8308ae4333f • 598MB • 4 days ago
1b-instruct-q4_0
71c75fff374b • 768MB • 4 days ago
1b-instruct-q4_1
266333af8965 • 849MB • 4 days ago
1b-instruct-q4_K_M
4d7713e45fcb • 822MB • 4 days ago
1b-instruct-q4_K_S
ce0829f9473a • 775MB • 4 days ago
1b-instruct-q5_0
d2dbb56842ff • 929MB • 4 days ago
1b-instruct-q5_1
d379b2b90641 • 1.0GB • 4 days ago
1b-instruct-q5_K_M
aa86331336b3 • 956MB • 4 days ago
1b-instruct-q5_K_S
22122ae9b16e • 929MB • 4 days ago
1b-instruct-q6_K
2c99260b2572 • 1.1GB • 4 days ago
1b-instruct-q8_0
3269ce3e31ea • 1.4GB • 4 days ago
3b-instruct-fp16
cdedb7e7b102 • 6.6GB • 4 days ago
3b-instruct-q2_K
1ed55612e40e • 1.2GB • 4 days ago
3b-instruct-q3_K_L
27d67c12fdf2 • 1.7GB • 4 days ago
3b-instruct-q3_K_M
e7baaff75b70 • 1.6GB • 4 days ago
3b-instruct-q3_K_S
74aa8c50c1c0 • 1.5GB • 4 days ago
3b-instruct-q4_0
eecc7ddd71c7 • 1.9GB • 4 days ago
3b-instruct-q4_1
40f18a9511cc • 2.1GB • 4 days ago
3b-instruct-q4_K_M
df6f6578dba8 • 2.0GB • 4 days ago
3b-instruct-q4_K_S
d3ac4ce39055 • 1.9GB • 4 days ago
3b-instruct-q5_0
c20dd012dabd • 2.3GB • 4 days ago
3b-instruct-q5_1
19c6c590893c • 2.5GB • 4 days ago
3b-instruct-q5_K_M
efec60309ba6 • 2.4GB • 4 days ago
3b-instruct-q5_K_S
cd3872ff6631 • 2.3GB • 4 days ago
3b-instruct-q6_K
461cb7bb8417 • 2.7GB • 4 days ago
3b-instruct-q8_0
038f46903bbd • 3.5GB • 4 days ago