Can LFM2.5 VL 450M run on the RTX 3060 12GB?
Yes. At 8K context the best fit is F16, using about 1.9 GB of the 11.4 GB usable on the RTX 3060 12GB. Estimated speed ceiling: ~253 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 | 2139 |
| 3-bit (Q3_K_M) | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 1642 |
| 4-bit (Q4_K_M) • | 0.8 GB Fits | 0.8 GB Fits | 1.1 GB Fits | 1570 |
| 5-bit (Q5_K_M) • | 0.8 GB Fits | 0.9 GB Fits | 1.1 GB Fits | 1383 |
| 6-bit (Q6_K) • | 0.8 GB Fits | 0.9 GB Fits | 1.2 GB Fits | 1227 |
| 8-bit (Q8_0) • | 0.9 GB Fits | 1.0 GB Fits | 1.3 GB Fits | 949 |
| 16-bit (F16/BF16) • | 1.9 GB Fits | 1.9 GB Fits | 2.2 GB Fits | 253 |
• real GGUF file size from LiquidAI/LFM2.5-VL-450M-GGUF. Speed is a bandwidth ceiling (360 GB/s), not a benchmark. Methodology.
More
LFM2.5 VL 450M on every GPU and Mac · Every model that runs on the RTX 3060 12GB · Other models that fit 12 GB VRAM · Try other settings in the calculator
Data: Hugging Face Hub (LiquidAI/LFM2.5-VL-450M), NVIDIA specs. Data as of 2026-11-17.