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

1,822 Pulls Updated 14 hours ago

33 Tags

5d8ebcfcdb80 • 2.1GB • Updated 20 hours ago

881c120886f6 • 822MB • Updated 23 hours ago

latest

5d8ebcfcdb80 • 2.1GB • Updated yesterday

1b-instruct-fp16

dd8a59650137 • 2.7GB • Updated 23 hours ago

1b-instruct-q2_K

45fb71415761 • 512MB • Updated 23 hours ago

1b-instruct-q3_K_S

9c9f36fe7340 • 598MB • Updated 23 hours ago

1b-instruct-q3_K_M

dbd52d52cd74 • 659MB • Updated 23 hours ago

1b-instruct-q3_K_L

0af587389b10 • 711MB • Updated 23 hours ago

1b-instruct-q4_0

2be1f58af678 • 768MB • Updated 23 hours ago

1b-instruct-q4_1

6be8cc180006 • 849MB • Updated 23 hours ago

1b-instruct-q4_K_S

df4c220e396c • 775MB • Updated 23 hours ago

1b-instruct-q4_K_M

881c120886f6 • 822MB • Updated 23 hours ago

1b-instruct-q5_0

8799d2971267 • 929MB • Updated 23 hours ago

1b-instruct-q5_1

d24e3bc11356 • 1.0GB • Updated 23 hours ago

1b-instruct-q5_K_S

476156f71010 • 929MB • Updated 23 hours ago

1b-instruct-q5_K_M

e490def0a321 • 956MB • Updated 23 hours ago

1b-instruct-q6_K

bf15431658f2 • 1.1GB • Updated 23 hours ago

1b-instruct-q8_0

dcbe47c2b7c4 • 1.4GB • Updated 23 hours ago

3b-instruct-fp16

7ea9827d7d07 • 6.8GB • Updated yesterday

3b-instruct-q2_K

da59c01b5ed1 • 1.3GB • Updated yesterday

3b-instruct-q3_K_S

007dc74c4762 • 1.5GB • Updated yesterday

3b-instruct-q3_K_M

e06ddcd361b7 • 1.6GB • Updated yesterday

3b-instruct-q3_K_L

c8f9673aa7d5 • 1.8GB • Updated yesterday

3b-instruct-q4_0

6daf78810309 • 1.9GB • Updated yesterday

3b-instruct-q4_1

c688d5ecbc67 • 2.1GB • Updated yesterday

3b-instruct-q4_K_S

f8121a6f0ac4 • 1.9GB • Updated yesterday

3b-instruct-q4_K_M

5d8ebcfcdb80 • 2.1GB • Updated yesterday

3b-instruct-q5_0

9522627e2632 • 2.3GB • Updated yesterday

3b-instruct-q5_1

4c12546d1fdc • 2.5GB • Updated yesterday

3b-instruct-q5_K_S

c34b92773d42 • 2.3GB • Updated yesterday

3b-instruct-q5_K_M

1c128c4b1bc6 • 2.4GB • Updated yesterday

3b-instruct-q6_K

a2a8e0a8bfa6 • 2.8GB • Updated yesterday

3b-instruct-q8_0

3a4ef96e5b97 • 3.6GB • Updated yesterday