Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Top downloads
Select 2-5 models
| Attribute |
ibm-granite
|
|---|---|
| Company | ibm-granite |
| Release Date | 2025-05-02 |
| Parameters (B) | 7 |
| Architecture | Hybrid MoE (Mamba-2/Transformer) |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 24 |
| Compute | Single consumer GPU with 16-24 GB VRAM (e.g., RTX 4090) for BF16 inference; 12 GB feasible with FP8 quantization |
| Benchmark: BBH | 55.7 |
| Benchmark: DROP | 46.2 |
| Benchmark: GSM8K | 70.0 |
| Benchmark: HumanEval | 82.4 |
| Benchmark: IFEval | 63.0 |
| Benchmark: MMLU | 60.4 |
| Benchmark: TruthfulQA | 58.1 |
| Pricing (Input) | — |
| Pricing (Output) | — |