LFM 2 8B A1B
LFM 2 8B A1B is Liquid AI's language model with a 33K context window. An efficient on-device Mixture-of-Experts LLM with 8.3B total parameters and ~1.5B active parameters, optimized for fast, high-quality inference on edge hardware.
Liquid AI's language model with a 33K context window. An efficient on-device Mixture-of-Experts LLM with 8.3B total parameters and ~1.5B active parameters, optimized for fast, high-quality inference on edge hardware.7.0#331 |
2.3#257 |
25.3#136 |
0.5#216 |
0.3#270 |
0.0#183 |
0.2#215 |
0.3#237 |
0.00s#85 |
0.1#291 |
0.3#136 |
0.0#255 |
0.0#251 |
0.1#239 |
0.0#291 |
Capabilities
Input1/5
✓
·
·
·
·
Output1/5
✓
·
·
·
·
Capabilities0/13
·
·
·
·
·
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.010 | $0.020 |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| LFM2.5-1.2B-Instruct | 33K | — | — | Available | |
| LFM2.5-1.2B-Thinking | 33K | — | — | Available | |
| LFM2.5-VL-1.6B | — | — | — | — | Available |
| LFM 2 24B A2B | 33K | $0.030 | $0.120 | Available | |
| LFM 2 8B A1B | 33K | — | — | Current | |
| LFM 2.2 6B | 33K | — | — | Available | |
| LFM2 1.2B | — | — | — | — | Available |
| LFM 40B | — | 131K | $0.100 | $0.200 | Available |
| LFM 7B | — | 131K | $0.025 | $0.040 | Available |