Can I Run LFM2.5 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Written by Jakub Rusinowski · Last updated October 15, 2026
Yes
Yes — LFM2.5-24B-A2B at Q6_K needs about 20.7 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) (~3.3 GB spare), at ~199.4 tok/s (estimated), with room for about 131,072 tokens of context.
Confidence: high · Recommended quantization: Q6_K · Estimated speed: ~199.4 tok/s
See what else this hardware can run →
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.
RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) — what it gives a model
| Usable memory for models | 24 GB |
| Memory bandwidth | 1008 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
LFM2.5 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM): memory by quantization
| Quant | Memory needed | Fits 24 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 | ✓ Yes | 128K | ~199.4 tok/s | 19.7 GB |
| Q5_K_M | 18 GB | ✓ Yes | 128K | ~214.9 tok/s | 17 GB |
| Q4_K_M | 15.5 GB | ✓ Yes | 128K | ~231.8 tok/s | 14.5 GB |
| Q3_K_M | 11.2 GB | ✓ Yes | 128K | ~267.5 tok/s | 10.2 GB |
| Q2_K | 8.8 GB | ✓ Yes | 128K | ~292.2 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 | ~231.8 tok/s |
| LFM2.5-8B-A1B | 7 GB | ✓ Fits | ~236.9 tok/s |
| LFM2.5 2.6B | 3.2 GB | ✓ Fits | ~203 tok/s |
RTX 4090 desktop limitations
- 24 GB is the sweet spot for 27–32B models at Q4; 70B needs offload or a second card.
Recommended setup
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 24 GB of VRAM on the NVIDIA GeForce RTX 4090 at 1008 GB/s.
- 64 GB of system RAM available for CPU offload when a model exceeds VRAM.
- 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 RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Yes — LFM2.5-24B-A2B at Q6_K needs about 20.7 GB of the 24 GB usable on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM) (~3.3 GB spare), at ~199.4 tok/s (estimated), with room for about 131,072 tokens of context.
Which quantization of LFM2.5 should I use on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Q6_K — it needs about 20.7 GB of the 24 GB available, downloads as roughly 19.7 GB, and runs at an estimated 199.4 tokens/sec with up to 128K of context.
What limits LFM2.5 on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Other Computers
Other Models on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Llama 3.1 Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Llama 3.2 Family on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Llama 3.2 Vision on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- Magistral Small on RTX 4090 Desktop (24 GB VRAM, 64 GB RAM)
- MiniCPM-V on RTX 4090 Desktop (24 GB VRAM, 64 GB 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