Model benchmarks
liquidai/lfm2.5-2.6b local LLM performance
As of August 2026, liquidai/lfm2.5-2.6b runs at up to 165.9 tok/s for local inference (best of 2 community benchmark runs across 1 GPU).
LM Studio
Model size
2.6B
Peak speed
165.9 tok/s
Average speed
132.7 tok/s
Min memory
2.7 GB
Max context
15,979 tokens
Best quality
86.0
Benchmark runs
2
GPUs tested
1
Performance by hardware and tool
Every hardware/tool/quantization combination liquidai/lfm2.5-2.6b has been benchmarked on, ranked by peak token generation speed. Last updated August 2026.
| Hardware | Tool | Quant | Best tok/s | Avg tok/s | Memory | Context | Quality | Runs |
|---|---|---|---|---|---|---|---|---|
| NVIDIA GeForce RTX 4070 Ti SUPER | LM Studio | — | 165.9 tok/s | 132.7 tok/s | 2.7 GB | 15,979 tokens | 50.6 | 2 |
Frequently asked questions
- How fast is liquidai/lfm2.5-2.6b for local inference?
- Across 2 community benchmark runs, liquidai/lfm2.5-2.6b reaches up to 165.9 tok/s and averages 132.7 tok/s, with the fastest results on NVIDIA GeForce RTX 4070 Ti SUPER.
- How much memory does liquidai/lfm2.5-2.6b need?
- The leanest observed configuration used about 2.7 GB of memory.
- Which tools have been used to run liquidai/lfm2.5-2.6b?
- Benchmarks were submitted using LM Studio. Results are community-contributed and updated as new runs arrive.