Can I Run LFM2.5 on 24 GB system RAM?
Written by Jakub Rusinowski · Last updated October 15, 2026
Yes, but it is tight
Yes, but it is tight — LFM2.5-24B-A2B at Q5_K_M needs about 18 GB of the 19.2 GB usable on 24 GB system RAM, leaving only ~1.2 GB before the runtime starts swapping. Expect ~34.1 tok/s (estimated), with room for about 65,536 tokens of context.
Confidence: medium · Recommended quantization: Q5_K_M · Estimated speed: ~34.1 tok/s
Get a personalized upgrade path →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
24 GB system RAM — what it gives a model
| Usable memory for models | 19.2 GB |
| Memory bandwidth | 90 GB/s |
LFM2.5 on 24 GB system RAM: memory by quantization
| Quant | Memory needed | Fits 19.2 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 48.9 GB | ✗ No | — | — | 48 GB |
| Q8_0 | 26.5 GB | ✗ No | — | — | 25.5 GB |
| Q6_K | 20.7 GB | ✗ No | — | — | 19.7 GB |
| Q5_K_M | 18 GB | ✓ Yes | 64K | ~34.1 tok/s | 17 GB |
| Q4_K_M | 15.5 GB | ✓ Yes | 128K | ~39.2 tok/s | 14.5 GB |
| Q3_K_M | 11.2 GB | ✓ Yes | 128K | ~52.5 tok/s | 10.2 GB |
| Q2_K | 8.8 GB | ✓ Yes | 128K | ~64.6 tok/s | 7.9 GB |
Which LFM2.5 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| LFM2.5-24B-A2B | 15.5 GB | ✓ Fits | ~39.2 tok/s |
| LFM2.5-8B-A1B | 7 GB | ✓ Fits | ~40.9 tok/s |
| LFM2.5 2.6B | 3.2 GB | ✓ Fits | ~30.9 tok/s |
What to watch out for
- Only ~1.2 GB of headroom at Q5_K_M: a longer context or a second application can push this into swapping.
- These figures assume CPU-only inference. Any discrete GPU, even an 8 GB one, will be several times faster for models that fit in its VRAM.
Recommended setup
llama.cpp (CPU build) or Ollama — both run without a GPU
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 19.2 GB of the 24 GB is treated as usable for model weights (80% — the rest is the OS and running applications).
- DDR5-5600 dual channel at 89.6 GB/s peak. CPU decode is assumed to sustain 35% of that peak, because CPU inference is not purely bandwidth-bound — it also spends real time in compute and thread synchronisation. This figure is an assumption, not a fitted constant: no CPU measurement is in the calibration set.
- CPU-only inference: no GPU is assumed. A GPU of any size will beat these figures substantially.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run LFM2.5 on 24 GB system RAM?
Yes, but it is tight — LFM2.5-24B-A2B at Q5_K_M needs about 18 GB of the 19.2 GB usable on 24 GB system RAM, leaving only ~1.2 GB before the runtime starts swapping. Expect ~34.1 tok/s (estimated), with room for about 65,536 tokens of context.
Which quantization of LFM2.5 should I use on 24 GB system RAM?
Q5_K_M — it needs about 18 GB of the 19.2 GB available, downloads as roughly 17 GB, and runs at an estimated 34.1 tokens/sec with up to 64K of context.
What limits LFM2.5 on 24 GB system RAM?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
llama.cpp (CPU build) or Ollama — both run without a GPU
Other RAM Capacities
Other Models on 24 GB system RAM
- Llama 3.1 Family on 24 GB system RAM
- Llama 3.2 Family on 24 GB system RAM
- Llama 3.2 Vision on 24 GB system RAM
- Magistral Small on 24 GB system RAM
- MiniCPM-V on 24 GB system RAM
LFM2.5 on GPUs
- LFM2.5 on NVIDIA GeForce RTX 5070
- LFM2.5 on NVIDIA GeForce RTX 5060 Ti 8GB
- LFM2.5 on NVIDIA GeForce RTX 5060
- LFM2.5 on NVIDIA GeForce RTX 4070 Ti