Loading…
Loading…
Models / mini-Ichigo-llama3.2
GPU memory needed (smallest version of each): mini-Ichigo-llama3.2 3B about 10.4 GB. The cheapest runs on RTX 3060 from $0.10/h right now.
2 models (3B to 3B) · ↓ 95 downloads a month · from $0.10/h on RTX 3060 right now. Each model's versions do the same job; quantized ones (AWQ, FP8, 4-bit) need less GPU memory and run on cheaper machines.
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalMenlo/mini-Ichigo-llama3.2-3B-s-instruct | vLLM | 6.4 GB | 10.4 GB | $0.10/h RTX 3060 |
| Version | Runtime | Weights | GPU memory | Cheapest machine now |
|---|---|---|---|---|
| OriginalMenlo/mini-Ichigo-llama3.2-3B-s-base | vLLM | 6.4 GB | 10.4 GB | $0.10/h RTX 3060 |
Model details come from Hugging Face and are refreshed daily; prices follow the live offers. GPU memory is GridPup's estimate: the weights, room for an 8,192-token conversation (chat models) and the runtime's own memory. Large models are split across the GPUs of one machine ("4x RTX 4090").