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 | 2026-07-29 |
| Parameters (B) | 35 |
| Architecture | Mobius-v0 MoE |
| Context Window | 262144 |
| Input Modalities | text, image |
| Open Source | Yes |
| License | apache-2.0 |
| Score | 0 |
| VRAM (GB) | 80 |
| Compute | Single NVIDIA A100/H100 80GB for bf16 inference (LMDeploy tp=1); 2x 80GB GPUs recommended for vLLM tensor parallelism |
| Benchmark: AIME-2026 | 95.3 |
| Benchmark: GPQA-Diamond | 80.8 |
| Benchmark: HLE | 19.1 |
| Benchmark: MMLU-Pro | 89.0 |
| Benchmark: SimpleQA | 28.9 |
| Pricing (Input) | — |
| Pricing (Output) | — |