LFM 2.5 1.2B Thinking is Liquid AI's language model with a 33K context window. A lightweight 1.2B-parameter reasoning-focused Liquid Foundation Model optimized for agentic tasks, data extraction, and RAG on edge devices.
| Benchmarks | |
|---|---|
| Intelligence Index | #510 |
| GPQA | #463 |
| HLE | #304 |
| IFBench | #245 |
| Time to First Token | #180 |
| SciCode | #493 |
| LCR | #444 |
| TerminalBench Hard | #396 |
| TAU2 | #341 |
| Output TPS | #415 |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
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 LFM 2.5 1.2B Thinking, ranked by cheapest on-demand price. The model needs about 3 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 | |||
| Standard_NV4ads_V710_v5 | AMD Radeon Pro V710 (24GB) | 4 GB | $0.333/hr | |||
| g5g.xlarge | T4g | 16 GB | $0.420/hr | |||
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| LFM 2 24B A2B | 128K | — | — | Available | |
| LFM 2.5 1.2B Thinking | 33K | — | — | Current | |
| LFM 2.5 1.2B Instruct | 33K | — | — | Available | |
| LFM 2.5 8B A1B | — | — | — | — | Available |
| LFM 2 2.6B | — | — | — | — | Available |
| LFM 2 8B A1B | — | — | — | — | Available |
| LFM 2 1.2B | — | — | — | — | Available |
| LFM 2.5 1.6B VL | — | — | — | — | Available |
| LFM 2.5 2.6B | 128K | — | — | Available | |
| LFM 40B | — | 131K | $0.100 | $0.200 | Available |
| LFM 7B | — | 131K | $0.025 | $0.040 | Available |