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.

Most downloadedNewestLargestLongest contextSmallest
GR
granite-4.2-8b
Granite · vultr
Params8.79B
Context128K
Q4_K_M5.8 GB
ReasoningTool use
QW
Qwen3.5-2B
Qwen · vultr
Params1.88B
Context256K
Q4_K_M1.4 GB
ReasoningTool useVision
LI
Ling-3.0-tiny
Ling · vultr
Params7.89B
Context128K
Q4_K_M5.3 GB
ReasoningTool use
QW
Qwen3.5-35B-A3B
Qwen · vultr
Params34.7B
Context256K
Q4_K_M23.3 GB
ReasoningTool useVision
GL
GLM 5.2
GLM · vultr
Params743B
Context1024K
Q4_K_M492.8 GB
ReasoningTool use
NE
NVIDIA-Nemotron-3-Super-120B-A12B
Nemotron · vultr
Params121B
Context1024K
Q4_K_M94.6 GB
ReasoningTool use
LI
Ling-3.0-flash-VL
Ling · vultr
Params124B
Context128K
Q4_K_M82.8 GB
ReasoningTool useVision
LI
Ling-3.0-flash-Fin
Ling · vultr
Params124B
Context256K
Q4_K_M82.8 GB
ReasoningTool use
LI
Ling-3.1-flash
Ling · vultr
Params564B
Context256K
Q4_K_M374.1 GB
ReasoningTool use
NE
Nemotron-3-Nano-Omni-30B-A3B-Reasoning
Nemotron · vultr
Params31.6B
Context1024K
Q4_K_M27.0 GB
ReasoningTool useVision
LI
Ling-3.0-flash-Sante
Ling · vultr
Params124B
Context256K
Q4_K_M82.8 GB
ReasoningTool use
MI
MiniMax-M2.7
Minimax · vultr
Params229B
Context200K
Q4_K_M152.1 GB
ReasoningTool use
MI
Mistral-Medium-3.5-128B
Mistral · vultr
Params125B
Context256K
Q4_K_M82.4 GB
ReasoningTool useVision
NE
NVIDIA-Nemotron-3-Ultra-550B-A55B
Nemotron · vultr
Params549B
Context1024K
Q4_K_M379.6 GB
ReasoningTool use
NE
Nex-N2.5-Pro
Nex · vultr
Params396B
Context256K
Q4_K_M264.4 GB
ReasoningTool useVision

Keep browsing