40 Downloads Updated 4 months ago
Updated 4 months ago
4 months ago
74cd611cb97d · 104GB ·
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.