RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can LFM3 VL 2B run on the RTX 4060?

Yes. At 8K context the best fit is Q8_0, using about 2.5 GB of the 7.6 GB usable on the RTX 4060. Estimated speed ceiling: ~147 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.4 GB Fits1.4 GB Fits1.7 GB Fits378
3-bit (Q3_K_M)1.6 GB Fits1.6 GB Fits1.9 GB Fits290
4-bit (Q4_K_M) •1.7 GB Fits1.8 GB Fits2.0 GB Fits247
5-bit (Q5_K_M) •1.9 GB Fits1.9 GB Fits2.2 GB Fits216
6-bit (Q6_K) •2.0 GB Fits2.1 GB Fits2.4 GB Fits191
8-bit (Q8_0) •2.4 GB Fits2.5 GB Fits2.7 GB Fits147
16-bit (F16/BF16) •7.2 GB Tight7.2 GB Tight7.5 GB Tight39

• real GGUF file size from LiquidAI/LFM3-VL-2B-GGUF. Speed is a bandwidth ceiling (272 GB/s), not a benchmark. Methodology.

More

LFM3 VL 2B on every GPU and Mac · Every model that runs on the RTX 4060 · Other models that fit 8 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (LiquidAI/LFM3-VL-2B), NVIDIA specs. Data as of 2026-11-17.