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 |
LiquidAI
|
|---|---|
| Company | LiquidAI |
| Release Date | 2026-06 |
| Parameters (B) | 1.2 |
| Architecture | LFM2.5 Hybrid (LIV + GQA) |
| Context Window | 32768 |
| Input Modalities | text |
| Open Source | Yes |
| License | other |
| Score | 0 |
| VRAM (GB) | 4 |
| Compute | 4GB+ VRAM for INT4 q4f16 (recommended); 8GB for Q8; 16GB for FP16; 32GB for FP32. Runs on CPU, GPU via ONNX Runtime, or WebGPU via Transformers.js. |
| Benchmark: GPQA | 28.7 |
| Benchmark: GSM8K | 62.2 |
| Benchmark: HumanEval | 49.4 |
| Benchmark: IFEval | 79.1 |
| Benchmark: MATH-500 | 62.8 |
| Benchmark: MMLU | 54.2 |
| Pricing (Input) | — |
| Pricing (Output) | — |