LFM2.5-1.2B-Instruct
by LiquidAI
1.2B params · text-generation · 614 likes · 144.4k downloads
LFM2.5-1.2B-Instruct is a 1.2B parameter model. At Q4 quantization it requires 1GB of VRAM. It runs comfortably on GeForce RTX 4090 (1121 tok/s), GeForce RTX 5090 (1682 tok/s), M4 Max 128GB (410 tok/s).
GPU compatibility
| GPU | VRAM | Q4 Decode | Verdict |
|---|---|---|---|
| GeForce RTX 4090 | 24GB | 1121 tok/s | comfortable |
| GeForce RTX 5090 | 32GB | 1682 tok/s | comfortable |
| M4 Max 128GB | 128GB | 410 tok/s | comfortable |
| M4 Pro 48GB | 48GB | 205 tok/s | comfortable |
| M4 Pro 24GB | 24GB | 205 tok/s | comfortable |
| A100 PCIe 80 GB | 80GB | 2055 tok/s | comfortable |
| H100 SXM5 80 GB | 80GB | 4134 tok/s | comfortable |
| GeForce RTX 3090 | 24GB | 991 tok/s | comfortable |
| Radeon RX 7900 XTX | 24GB | 820 tok/s | comfortable |
| GeForce RTX 4080 | 16GB | 796 tok/s | comfortable |