RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can LFM2.5 2.6B run on the RTX 4080?

Yes. At 8K context the best fit is F16, using about 10.8 GB of the 15.2 GB usable on the RTX 4080. Estimated speed ceiling: ~66 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.6 GB Fits1.7 GB Fits2.1 GB Fits3.6 GB Fits709
3-bit (Q3_K_M)1.9 GB Fits2.0 GB Fits2.4 GB Fits3.9 GB Fits544
4-bit (Q4_K_M) •2.3 GB Fits2.3 GB Fits2.7 GB Fits4.2 GB Fits428
5-bit (Q5_K_M) •2.5 GB Fits2.6 GB Fits3.0 GB Fits4.5 GB Fits370
6-bit (Q6_K) •2.8 GB Fits2.8 GB Fits3.2 GB Fits4.7 GB Fits323
8-bit (Q8_0) •3.4 GB Fits3.4 GB Fits3.8 GB Fits5.3 GB Fits249
16-bit (F16/BF16) •10.8 GB Fits10.8 GB Fits11.2 GB Fits12.7 GB Fits66

• real GGUF file size from LiquidAI/LFM2.5-2.6B-GGUF. Speed is a bandwidth ceiling (717 GB/s), not a benchmark. Methodology.

More

LFM2.5 2.6B on every GPU and Mac · Every model that runs on the RTX 4080 · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (LiquidAI/LFM2.5-2.6B), NVIDIA specs. Data as of 2026-11-17.