Liquid AI · 1.7B · Dense
Edge agent model for tool calling and structured outputs — about 1 GB at 4-bit, 256K context Check if your GPU or Mac can run LFM3 1.7B locally — 1 GB min, 2 GB recommended.
2026-10256K context
| Quant | Bits | VRAM | Quality | Status |
|---|---|---|---|---|
| Q2_K | 2 | 1 GB | low | — |
| Q3_K_M | 3 | 1.3 GB | moderate | — |
| Q4_K_M | 4 | 1.4 GB | good | — |
| Q5_K_M | 5 | 1.6 GB | good | — |
| Q6_K | 6 | 1.8 GB | excellent | — |
| Q8_0 | 8 | 2.2 GB | excellent | — |
| F16 | 16 | 4 GB | lossless | — |
Can I run LFM3 1.7B locally?
- Can I run LFM3 1.7B locally?
- LFM3 1.7B needs about 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 LFM3 1.7B need?
- At Q4_K_M, LFM3 1.7B uses about 1.4 GB of VRAM. Higher quants need more memory; lower quants fit tighter cards with a quality tradeoff.