Compare LLM Models
Select 2-5 models to compare side by side.
Select models to compare
0 / 5 selected
Select 2-5 models
| Attribute |
tokyotech-llm
|
|---|---|
| Company | tokyotech-llm |
| Release Date | 2025-06-25 |
| Parameters (B) | 8 |
| Architecture | Llama 3.1 (decoder-only Transformer) |
| Context Window | 128000 |
| Input Modalities | text |
| Open Source | Yes |
| License | |
| Score | 8.2 |
| VRAM (GB) | 16 |
| Compute | Single GPU with 16GB+ VRAM (e.g., RTX 4090, A10, L4) for BF16/FP16 inference; supports vLLM and HuggingFace Transformers with tensor_parallel_size=1 |
| Benchmark: GSM8K | 71.7 |
| Benchmark: HumanEval | 55.4 |
| Benchmark: MMLU | 66.3 |
| Pricing (Input) | — |
| Pricing (Output) | — |