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) | 8.2 |
| Architecture | Transformer |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | Single NVIDIA GPU with ≥16GB VRAM for BF16 inference; AWQ-INT4 quantized variant available for ~8GB VRAM |
| Benchmark: GPQA | 58.3 |
| Benchmark: HellaSwag | 79.3 |
| Benchmark: LiveCodeBench | 52.1 |
| Benchmark: MATH-500 | 94.4 |
| Benchmark: MMLU-Pro | 69.8 |
| Pricing (Input) | — |
| Pricing (Output) | — |