RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?API pricesVRAM calculatorNew

Can LFM2.5 VL 3B run on the RTX 3080 10GB?

Yes. At 8K context the best fit is F16, using about 5.8 GB of the 9.5 GB usable on the RTX 3080 10GB. Estimated speed ceiling: ~141 tokens/sec.

+ 0.5 GB with image input. The figures on this page are for text only. Sending images also loads the vision projector (mmproj) file: F16 at 8K context then needs about 6.3 GB (still fits). Calculator with image input on.

Memory by quant and context

Quant4K ctx8K ctx32K ctxMax tok/s (est., 8K)
2-bit (Q2_K)1.8 GB Fits1.9 GB Fits2.2 GB Fits649
3-bit (Q3_K_M)2.1 GB Fits2.2 GB Fits2.6 GB Fits498
4-bit (Q4_K_M) •2.3 GB Fits2.3 GB Fits2.7 GB Fits454
5-bit (Q5_K_M) •2.5 GB Fits2.6 GB Fits3.0 GB Fits392
6-bit (Q6_K) •2.8 GB Fits2.8 GB Fits3.2 GB Fits342
8-bit (Q8_0) •3.4 GB Fits3.4 GB Fits3.8 GB Fits264
16-bit (F16/BF16) •5.7 GB Fits5.8 GB Fits6.2 GB Fits141

• real GGUF file size from LiquidAI/LFM2.5-VL-3B-GGUF. Speed is a bandwidth ceiling (760 GB/s), not a benchmark. Methodology.

What fits instead

"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 3B on every GPU and Mac · Every model that runs on the RTX 3080 10GB · Other models that fit 12 GB VRAM · 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-3B), NVIDIA specs. Model data last checked 2026-11-17; refreshed hourly.