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 |
tokyotech-llm
|
|---|---|
| Company | tokyotech-llm |
| Release Date | 2026-02-20 |
| Parameters (B) | 32 |
| Architecture | Transformer |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 64 |
| Compute | 1x NVIDIA A100 80GB or 2x A100 40GB for BF16 inference; AWQ-INT4 variant runs on a single 24GB GPU |
| Benchmark: AIME-2024 | 82.5 |
| Benchmark: GPQA | 70.1 |
| Benchmark: HellaSwag | 88.8 |
| Benchmark: HumanEval | 92.9 |
| Benchmark: IFEval | 52.9 |
| Benchmark: LiveCodeBench | 63.8 |
| Benchmark: MATH-500 | 98.2 |
| Benchmark: MMLU-Pro | 77.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |