Liquid AI · 1.9B · Dense
On-device decision model on LFM3-VL — millisecond calibrated answers over text, pictures and video Check if your GPU or Mac can run d1 2B locally — 1.1 GB min, 2 GB recommended.
2026-10125K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 1.1 GB | low | — |
| Q3_K_M | 3 | 1.4 GB | moderate | — |
| Q4_K_M | 4 | 1.5 GB | good | — |
| Q5_K_M | 5 | 1.7 GB | good | — |
| Q6_K | 6 | 2 GB | excellent | — |
| Q8_0 | 8 | 2.4 GB | excellent | — |
| F16 | 16 | 4.4 GB | lossless | — |
Can I run d1 2B locally?
- Can I run d1 2B locally?
- d1 2B needs about 1.1 GB of memory at a minimum and 2 GB recommended. Open this page to grade it against your GPU or Mac, then run it with runai, Ollama or LM Studio.
- How much VRAM does d1 2B need?
- At Q4_K_M, d1 2B uses about 1.5 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.