GGUF models by TheBloke
1062 GGUF models quantized by TheBloke on Hugging Face. Sizes run from 1.1B to 124B parameters. The longest trained context is 195K tokens.
TA
Tai 70B
Tai · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
VE
Venus 103b v1.1
Venus · TheBloke
Params103B
Context4K
Smallest43.5 GB
LL
undi95_llamix2-mlewd-4x13b
Llamix · TheBloke
Params38.5B
Context32K
Smallest21.7 GB
CU
cutie
Cutie · TheBloke
Params7.24B
Context4K
Q4_K_M4.4 GB
ME
Megamix A1 13B
Megamix · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
SO
Solus 70B L2
Solus · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
MA
Marcoroni 70B v1
Marcoroni · TheBloke
Params69B
Context4K
Q4_K_M41.4 GB
LI
Lila 103B L2
Lila · TheBloke
Params103B
Context4K
Smallest43.5 GB
UN
UndiMix v4 13B
Undimix · TheBloke
Params13B
Context4K
Q4_K_M7.9 GB
TE
Tess XL v1.0
Tess · TheBloke
Params118B
Context4K
Smallest49.6 GB
VE
Venus 103b v1.2
Venus · TheBloke
Params103B
Context4K
Smallest43.5 GB
WI
WinterGoliath 123b
Wintergoliath · TheBloke
Params124B
Context4K
Smallest45.3 GB