granite3-moe

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

tools 1b 3b

20.8K 4 weeks ago

33 Tags
latest
d84e1e38ee39 • 822MB • 4 weeks ago
1b
d84e1e38ee39 • 822MB • 4 weeks ago
3b
157f538ae66e • 2.1GB • 4 weeks ago
1b-instruct-fp16
cee5d696574c • 2.7GB • 4 weeks ago
1b-instruct-q2_K
5965f707577c • 512MB • 4 weeks ago
1b-instruct-q3_K_L
bbb955565d3d • 711MB • 4 weeks ago
1b-instruct-q3_K_M
ea6a79b9b3cc • 659MB • 4 weeks ago
1b-instruct-q3_K_S
cab9e1d32d19 • 598MB • 4 weeks ago
1b-instruct-q4_0
9b6ee4c08df8 • 768MB • 4 weeks ago
1b-instruct-q4_1
c3aa5d722767 • 849MB • 4 weeks ago
1b-instruct-q4_K_M
d84e1e38ee39 • 822MB • 4 weeks ago
1b-instruct-q4_K_S
76e6392d08a3 • 775MB • 4 weeks ago
1b-instruct-q5_0
f49b9c68d958 • 929MB • 4 weeks ago
1b-instruct-q5_1
f1dbdb4ce40f • 1.0GB • 4 weeks ago
1b-instruct-q5_K_M
c51ea1c8bab3 • 956MB • 4 weeks ago
1b-instruct-q5_K_S
427124d0793f • 929MB • 4 weeks ago
1b-instruct-q6_K
a585cc84307b • 1.1GB • 4 weeks ago
1b-instruct-q8_0
84f7efa9cc2d • 1.4GB • 4 weeks ago
3b-instruct-fp16
9433d98bf426 • 6.8GB • 4 weeks ago
3b-instruct-q2_K
48ee4c1b7090 • 1.3GB • 4 weeks ago
3b-instruct-q3_K_L
8c76215f504a • 1.8GB • 4 weeks ago
3b-instruct-q3_K_M
cc32cde7c1fe • 1.6GB • 4 weeks ago
3b-instruct-q3_K_S
5952b23cdd5c • 1.5GB • 4 weeks ago
3b-instruct-q4_0
d144aac2b0d8 • 1.9GB • 4 weeks ago
3b-instruct-q4_1
ac91c7b62cc7 • 2.1GB • 4 weeks ago
3b-instruct-q4_K_M
157f538ae66e • 2.1GB • 4 weeks ago
3b-instruct-q4_K_S
9f5ecea51621 • 1.9GB • 4 weeks ago
3b-instruct-q5_0
e623edd5db90 • 2.3GB • 4 weeks ago
3b-instruct-q5_1
709d47478efd • 2.5GB • 4 weeks ago
3b-instruct-q5_K_M
94e89b071306 • 2.4GB • 4 weeks ago
3b-instruct-q5_K_S
c84b2a3a27fd • 2.3GB • 4 weeks ago
3b-instruct-q6_K
c196db4b29bb • 2.8GB • 4 weeks ago
3b-instruct-q8_0
f3b962d19110 • 3.6GB • 4 weeks ago