9 Downloads Updated 3 weeks ago
ollama run edtorre/gemma4-256k
ollama launch claude --model edtorre/gemma4-256k
ollama launch opencode --model edtorre/gemma4-256k
ollama launch hermes --model edtorre/gemma4-256k
ollama launch openclaw --model edtorre/gemma4-256k
A lightweight, agent-tuned Gemma 4 12B model built for local agent harnesses like Hermes Agent. Based on gemma4:12b-it-qat with Q4_0 quantization but with the max 256k context window.
| Parameter | Value | |—————–|—————————————-| | Base Model | gemma4:12b-it-qat | | Parameters | 11.9B | | Quantization | Q4_0 | | Size | 8.1 GB | | Context Window | 256k | | Max Output | 8,192 tokens | | Temperature | 0.7 | | Top-k / Top-p | 40 / 0.9 |