RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can LFM2.5 24B A2B run on the RX 7800 XT?

Yes. At 8K context the best fit is Q3_K_M, using about 11.7 GB of the 15.2 GB usable on the RX 7800 XT. Estimated speed ceiling: ~638 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)9.1 GB Fits9.2 GB Fits9.6 GB Fits11.5 GB Fits832
3-bit (Q3_K_M)11.6 GB Fits11.7 GB Fits12.2 GB Fits14.1 GB Tight638
4-bit (Q4_K_M) •14.3 GB Tight14.3 GB Tight14.8 GB Tight16.7 GB No515
5-bit (Q5_K_M) •16.6 GB No16.7 GB No17.1 GB No19.0 GB No—
6-bit (Q6_K) •19.1 GB No19.1 GB No19.6 GB No21.5 GB No—
8-bit (Q8_0) •24.5 GB No24.5 GB No25.0 GB No26.9 GB No—
16-bit (F16/BF16) •90.1 GB No90.1 GB No90.6 GB No92.5 GB No—

• real GGUF file size from LiquidAI/LFM2.5-24B-A2B-GGUF. Speed is a bandwidth ceiling (624 GB/s), not a benchmark. Methodology.

More

LFM2.5 24B A2B on every GPU and Mac · Every model that runs on the RX 7800 XT · Other models that fit 16 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (LiquidAI/LFM2.5-24B-A2B), AMD specs. Data as of 2026-11-17.