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 |
| Architecture | Transformer |
| Context Window | 32768 |
| Input Modalities | text |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 16 |
| Compute | Single NVIDIA GPU with 16GB+ VRAM (e.g. RTX 4090 or A10); BF16 weights (~16GB); vLLM recommended for inference |
| Benchmark: GPQA | 49.6 |
| Benchmark: HellaSwag | 79 |
| Benchmark: IFEval | 30.8 |
| Benchmark: LiveCodeBench | 34.2 |
| Benchmark: MATH-500 | 86 |
| Benchmark: MMLU-Pro | 62.4 |
| Pricing (Input) | — |
| Pricing (Output) | — |