Reasoning model for deliberate analysis, multi-step problem solving, and tool use
Details
| Field | Value |
|---|---|
| id | NousResearch/Hermes-4-70B |
| modality | text->text |
| context_length | 128000 |
| max_input_tokens | 120000 |
| max_output_tokens | 8192 |
| quantization | fp8 |
| knowledge_cutoff | 2025-11 |
| release_date | 2026-01-30 |
| is_open_weights | yes |
| supports_tool_call | yes |
| supports_reasoning | yes |
| supports_structured_output | yes |
| supports_attachment | no |
| input_modalities | text |
| output_modalities | text |