RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can LFM2.5 1.2B Instruct run on the Ryzen AI Max+ 395 128GB?

Yes. At 8K context the best fit is F16, using about 5.0 GB of the 109 GB usable on the Ryzen AI Max+ 395 128GB. Estimated speed ceiling: ~55 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.0 GB Fits1.0 GB Fits1.3 GB Fits583
3-bit (Q3_K_M)1.1 GB Fits1.2 GB Fits1.4 GB Fits448
4-bit (Q4_K_M) •1.3 GB Fits1.3 GB Fits1.6 GB Fits350
5-bit (Q5_K_M) •1.4 GB Fits1.4 GB Fits1.7 GB Fits304
6-bit (Q6_K) •1.5 GB Fits1.5 GB Fits1.8 GB Fits266
8-bit (Q8_0) •1.7 GB Fits1.8 GB Fits2.1 GB Fits205
16-bit (F16/BF16) •4.9 GB Fits5.0 GB Fits5.3 GB Fits55

• real GGUF file size from LiquidAI/LFM2.5-1.2B-Instruct-GGUF. Speed is a bandwidth ceiling (256 GB/s), not a benchmark. Methodology.

More

LFM2.5 1.2B Instruct on every GPU and Mac · Every model that runs on the Ryzen AI Max+ 395 128GB · Other models that fit 64 GB VRAM · Try other settings in the calculator

Data: Hugging Face Hub (LiquidAI/LFM2.5-1.2B-Instruct), AMD specs. Data as of 2026-11-17.