Can RTX 3060 12GB run LFM2.5 24B-A2B?
Partly: part of the model runs from system RAM (CPU offload, per the source). Measured 125 tok/s generation with part of the model offloaded to system RAM (llama.cpp, llama-bench tg128 (quant per result); source).
Every measured result for LFM2.5 24B-A2B on RTX 3060 12GB
| Build | Quant / setup | Engine | tok/s | |
|---|---|---|---|---|
| RTX 3060 12GB: 2026 models (llamabench community) | llama-bench tg128 (quant per result) | llama.cpp | 125 CPU offload | source |
Memory: RTX 3060 12GB has 12 GB. LFM2.5 24B-A2B weights are about 14.7 GB at Q4_K_M (23.97B params × 4.89 bits ÷ 8, before context/KV cache). Arithmetic, not a measurement; long contexts need more. Check other quants in the VRAM calculator.
Speeds are decode (generation) tokens/sec as reported by each source; quant, engine and context differ, so small gaps are noise.
All measured speeds for LFM2.5 24B-A2B: best home rig for LFM2.5 24B-A2B.
LFM2.5 24B-A2B on other hardware: RTX 4060 Ti 16GB · RTX 4090
Other models measured on RTX 3060 12GB: Gemma 4 12B · Qwen3.8 27B · gpt-oss 20B
Not enough VRAM? Rent before you buy. Run LFM2.5 24B-A2B on a bigger GPU on a rented 24–96 GB cloud GPU by the hour and see the real speed before spending €1,000+. Try it on Runpod
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.
Referral link: if you sign up with Google and add $10, Runpod gives you and RigBase bonus credit (terms). It never affects our data.