GGUF models by vultr
35 GGUF models quantized by vultr on Hugging Face. Sizes run from 3.66B to 743B parameters. The longest trained context is 1024K tokens.
GR
granite-4.2-8b
Granite · vultr
Params8.79B
Context128K
Q4_K_M5.8 GB
QW
Qwen3.5-2B
Qwen · vultr
Params1.88B
Context256K
Q4_K_M1.4 GB
LI
Ling-3.0-tiny
Ling · vultr
Params7.89B
Context128K
Q4_K_M5.3 GB
QW
Qwen3.5-35B-A3B
Qwen · vultr
Params34.7B
Context256K
Q4_K_M23.3 GB
GL
GLM 5.2
GLM · vultr
Params743B
Context1024K
Q4_K_M492.8 GB
NE
NVIDIA-Nemotron-3-Super-120B-A12B
Nemotron · vultr
Params121B
Context1024K
Q4_K_M94.6 GB
LI
Ling-3.0-flash-VL
Ling · vultr
Params124B
Context128K
Q4_K_M82.8 GB
LI
Ling-3.0-flash-Fin
Ling · vultr
Params124B
Context256K
Q4_K_M82.8 GB
LI
Ling-3.1-flash
Ling · vultr
Params564B
Context256K
Q4_K_M374.1 GB
NE
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron · vultr
Params31.6B
Context1024K
Q4_K_M27.0 GB
LI
Ling-3.0-flash-Sante
Ling · vultr
Params124B
Context256K
Q4_K_M82.8 GB
MI
MiniMax-M2.7
Minimax · vultr
Params229B
Context200K
Q4_K_M152.1 GB
MI
Mistral-Medium-3.5-128B
Mistral · vultr
Params125B
Context256K
Q4_K_M82.4 GB
NE
NVIDIA-Nemotron-3-Ultra-550B-A55B
Nemotron · vultr
Params549B
Context1024K
Q4_K_M379.6 GB
NE
Nex-N2.5-Pro
Nex · vultr
Params396B
Context256K
Q4_K_M264.4 GB