RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can LFM3 1.7B run on the RTX 4080 Super?

Yes. At 8K context the best fit is F16, using about 7.2 GB of the 15.2 GB usable on the RTX 4080 Super. Estimated speed ceiling: ~106 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.3 GB Fits1.3 GB Fits1.6 GB Fits2.8 GB Fits1135
3-bit (Q3_K_M)1.5 GB Fits1.5 GB Fits1.8 GB Fits2.9 GB Fits871
4-bit (Q4_K_M) •1.7 GB Fits1.8 GB Fits2.0 GB Fits3.2 GB Fits669
5-bit (Q5_K_M) •1.9 GB Fits1.9 GB Fits2.2 GB Fits3.3 GB Fits585
6-bit (Q6_K) •2.0 GB Fits2.1 GB Fits2.4 GB Fits3.5 GB Fits516
8-bit (Q8_0) •2.4 GB Fits2.5 GB Fits2.7 GB Fits3.9 GB Fits399
16-bit (F16/BF16) •7.2 GB Fits7.2 GB Fits7.5 GB Fits8.6 GB Fits106

• real GGUF file size from LiquidAI/LFM3-1.7B-GGUF. Speed is a bandwidth ceiling (736 GB/s), not a benchmark. Methodology.

More

LFM3 1.7B on every GPU and Mac · Every model that runs on the RTX 4080 Super · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (LiquidAI/LFM3-1.7B), NVIDIA specs. Data as of 2026-11-17.