LFM3 2B VL is Liquid AI's language model. Compact 2B vision-language Liquid Foundation Model for on-device image and text understanding.
| Benchmarks | |
|---|---|
| Intelligence Index | #80 |
| Time to First Token | #364 |
| Output TPS | #7 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Cheapest Instances to Run It
Cloud GPU instances that can host LFM3 2B VL, ranked by cheapest on-demand price. The model needs about 5 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NV4as_v4 | AMD Radeon Instinct MI25 | 16 GB | $0.233/hr | |||
| g5g.xlarge | T4g | 16 GB | $0.420/hr | |||
| Standard_NV8as_v4 | AMD Radeon Instinct MI25 | 16 GB | $0.466/hr | |||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| LFM3 1.7B | 262K | $0.080 | $0.200 | Available | |
| LFM3 2B VL | — | — | — | — | Current |
| LFM D1.2 | 66K | $0.020 | — | Available | |
| LFM D1.2 Ultra | 66K | $0.042 | — | Available | |
| LFM 2.5 24B A2B | 128K | $0.050 | $0.700 | Available | |
| LFM 2 24B A2B | 128K | — | — | Available | |
| LFM 2.5 1.2B Instruct | 33K | $0.020 | $0.050 | Available | |
| LFM 2.5 1.2B Thinking | 33K | $0.020 | $0.050 | Available | |
| LFM 2 1.2B | — | — | — | — | Available |
| LFM 2 2.6B | — | — | — | — | Available |
| LFM 2 8B A1B | — | — | — | — | Available |