40 Downloads Updated 4 months ago
Name
1 model
Size
Context
Input
qwen3-ud-q3:235b
104GB · 40K context window · Text · 4 months ago
104GB
40K
Text
Merged gguf files from Unsloth’s Q3_K_XL from Qwen3:255b using the default modelfile with the recommended settings from Qwen.
This model will take about ~110GB VRAM with the default context window of 4096 tokens.