The user says they used LoRA in Unsloth AI Studio on a rig with 16 GB of VRAM.
A user says they fine-tuned their own decision model using Gemma 4 E2B and LoRA in Unsloth AI Studio. They report that the full run took about 12 minutes on an old gaming rig with 16 GB of VRAM, and say the barrier to fine-tuning is lower than newcomers might think.
6.3K
2 Sources, first seen ago
@SeraAndroidFine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VRAM, about 12 minutes for the run in total. If you've never fine-tuned a model, this is your sign. The barrier is a lot lower than you think.
@ClementDelangueRT @SeraAndroid: Fine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VR…@SeraAndroidFine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VRAM, about 12 minutes for the run in total. If you've never fine-tuned a model, this is your sign. The barrier is a lot lower than you think.@ClementDelangueRT @SeraAndroid: Fine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VR…@SeraAndroidFine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VRAM, about 12 minutes for the run in total. If you've never fine-tuned a model, this is your sign. The barrier is a lot lower than you think.@ClementDelangueRT @SeraAndroid: Fine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VR…@SeraAndroidFine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VRAM, about 12 minutes for the run in total. If you've never fine-tuned a model, this is your sign. The barrier is a lot lower than you think.@ClementDelangueRT @SeraAndroid: Fine-tuning my own decision model on my old gaming rig: @googlegemma Gemma 4 E2B + LoRA in @UnslothAI Studio. 16 GB of VR…—
Not ranked yet
—
Not ranked yet
