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 |
internlm
|
|---|---|
| Company | internlm |
| Release Date | 2024-08-05 |
| Parameters (B) | 1.8 |
| Architecture | Transformer |
| Context Window | 32768 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 4.2 |
| Compute | Runs on consumer GPUs with ~4 GB VRAM in FP16; Q4 GGUF quantization reduces requirement to ~1.2 GB. Also deployable via LMDeploy, vLLM, or llama.cpp on CPU or low-end GPUs. |
| Benchmark: BBH | 41.9 |
| Benchmark: GPQA | 27.8 |
| Benchmark: MATH | 40.2 |
| Benchmark: MMLU | 50.7 |
| Pricing (Input) | — |
| Pricing (Output) | — |