Model
Google
Gemma 4 31B ITGemma 4 31B IT is a dense multimodal decoder-only transformer in the Eevee / Gemma 4 family designed for reasoning, coding assistance, multimodal understanding, and agentic workflows
By downloading or using the Model, you agree to the terms of the licenses linked to this page.
Copied!
| Name | Size | Updated | Actions |
|---|---|---|---|
chat_template.jinja | 16.54 KB | June 1, 2026 UTC | |
checksums.blake3 | 1.14 KB | June 1, 2026 UTC | |
config.json | 9.24 KB | June 1, 2026 UTC | |
generation_config.json | 208 B | June 1, 2026 UTC | |
hf_quant_config.json | 3.66 KB | June 1, 2026 UTC | |
model-00001-of-00004.safetensors | 9.27 GB | June 1, 2026 UTC | |
model-00002-of-00004.safetensors | 9.29 GB | June 1, 2026 UTC | |
model-00003-of-00004.safetensors | 9.31 GB | June 1, 2026 UTC | |
model-00004-of-00004.safetensors | 2.52 GB | June 1, 2026 UTC | |
model.safetensors.index.json | 170.43 KB | June 1, 2026 UTC | |
processor_config.json | 1.65 KB | June 1, 2026 UTC | |
README.md | 7.35 KB | June 1, 2026 UTC | |
tokenizer_config.json | 2.04 KB | June 1, 2026 UTC | |
tokenizer.json | 30.68 MB | June 1, 2026 UTC |