Compare / LFM2.5 1.2B Instruct vs LFM2.5 350M
LFM2.5 1.2B Instruct vs LFM2.5 350M
Updated November 2026
Verdict
LFM2.5 1.2B Instruct scores higher on the Small LM Index: 20.6 vs 12.6. On the 5 benchmarks both labs report, LFM2.5 1.2B Instruct wins 5 and LFM2.5 350M wins 0. Both need about 1.3 GB of memory at 4-bit quantization. Neither model has a hosted API on OpenRouter, so you would run both yourself.
Pick LFM2.5 1.2B Instruct if…
- you want the strongest model overall
- you need precise instruction following
- you build agents that call tools
Pick LFM2.5 350M if…
No clear advantage in the data we have.
Specifications
| LFM2.5 1.2B Instruct | LFM2.5 350M | |
|---|---|---|
| Small LM Index | 20.6 (likely 18–24) | 12.6 (likely 10–17) |
| Lab | Liquid AI · United States | Liquid AI · United States |
| Released | 2026-01-06 | 2026-03-31 |
| Parameters | 1.2B (dense) | 350M (dense) |
| Memory at 4-bit | ~1.3 GB | ~0.8 GB |
| Context window | 32K tokens | 32K tokens |
| Input | text | text |
| Reasoning | No thinking | No thinking |
| License | LFM Open License | LFM Open License |
| API price / 1M tokens | Self-host only | Self-host only |
| Hugging Face downloads (30 days) | 122.7K | 114K |
Benchmarks
Higher is better. Bold marks the winner where both labs report a score. ≈ marks the index model's estimate for a score that wasn't reported, ✓ an independent measurement and * a score measured by another lab.
| Benchmark | LFM2.5 1.2B Instruct | LFM2.5 350M |
|---|---|---|
| MMLU-Pro Knowledge | 44.4 | 20.0 |
| GPQA Diamond Knowledge | 38.9 | 30.6 |
| AIME Math | 14.0 | ≈ 6 |
| τ²-Bench Agentic | — | 18.4 |
| IFBench Instruction following | 47.3 | 40.7 |
| IFEval Instruction following | 86.2 | 77.0 |
| BFCL Agentic | 49.1 | 21.9 |
Scores are mostly reported by each lab with its own settings, so small gaps are noise. See the methodology. Open in the interactive comparison to add more models.
Questions
Which is better, LFM2.5 1.2B Instruct or LFM2.5 350M?
LFM2.5 1.2B Instruct scores higher on the Small LM Index: 20.6 vs 12.6. On the 5 benchmarks both labs report, LFM2.5 1.2B Instruct wins 5 and LFM2.5 350M wins 0.
Which is cheaper to run?
Neither model has a hosted API on OpenRouter, so you would run both yourself. Both need about 1.3 GB of memory at 4-bit quantization.
Which has the longer context window?
Both have a 32K-token context window.
Can I use LFM2.5 1.2B Instruct and LFM2.5 350M commercially?
Both are released under the LFM Open License license. Apache 2.0 and MIT allow commercial use; other licenses can add conditions, so read the license before shipping a product.