Can LFM2.5 VL 450M run on the 2x RTX 5090?
Yes. At 8K context the best fit is F16, using about 1.9 GB of the 60.8 GB usable on the 2x RTX 5090. Estimated speed ceiling: ~1259 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|
| 2-bit (Q2_K) | 0.7 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 10650 |
| 3-bit (Q3_K_M) | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 8171 |
| 4-bit (Q4_K_M) • | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 7815 |
| 5-bit (Q5_K_M) • | 0.8 GB Fits | 0.9 GB Fits | 1.1 GB Fits | 6882 |
| 6-bit (Q6_K) • | 0.8 GB Fits | 0.9 GB Fits | 1.2 GB Fits | 6108 |
| 8-bit (Q8_0) • | 0.9 GB Fits | 1.0 GB Fits | 1.3 GB Fits | 4726 |
| 16-bit (F16/BF16) • | 1.9 GB Fits | 1.9 GB Fits | 2.2 GB Fits | 1259 |
• real GGUF file size from LiquidAI/LFM2.5-VL-450M-GGUF. Speed is a bandwidth ceiling (1792 GB/s), not a benchmark. Methodology.
What fits instead
- Cheapest listed GPU that runs LFM2.5 VL 450M: Arc B580 (12 GB, launch MSRP $249) at F16, fully in VRAM at 8K context.
- Largest popular model that fits the 2x RTX 5090: Qwen3.6 35B A3B (36B, MoE) at Q8_0, about 36.2 GB at 8K context.
"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.
More
LFM2.5 VL 450M on every GPU and Mac · Every model that runs on the 2x RTX 5090 · Try other settings in the calculator
Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs
Data: Hugging Face Hub (LiquidAI/LFM2.5-VL-450M), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.