Can I run LFM3-VL-2B-GGUF on an RTX 6000 Ada?

Yes

Its BF16 file (3.47 GB) fits in the 43.2 GB an RTX 6000 Ada can use, with room for ≈ 125K tokens of context.

Full analysis of LFM3-VL-2B-GGUF Everything that runs on RTX 6000 Ada Get the BF16 file on Hugging Face

ollama run hf.co/LiquidAI/LFM3-VL-2B-GGUF:BF16

Files and context on RTX 6000 Ada

Each file of LFM3-VL-2B-GGUF (and of GGUF versions the site has analyzed), and how much context fits next to it, with the context cache in 16-bit or 8-bit.

File	Size	On RTX 6000 Ada	Context (16-bit)	Context (8-bit)
BF16	3.47 GB	Fits	125K	125K
F16	3.47 GB	Fits	125K	125K
Q8_0	1.85 GB	Fits	125K	125K
Q6_K	1.43 GB	Fits	125K	125K
LFM3-VL-2B-NVFP4	1.28 GB	Fits	125K	125K
Q5_K_M	1.26 GB	Fits	125K	125K
Q4_K_M	1.10 GB	Fits	125K	125K
Q4_0	1.05 GB	Fits	125K	125K

LFM3-VL-2B-GGUF on other hardware

Popular models that run on RTX 6000 Ada

Assumes 90% of the card's memory is usable and at least 4K tokens of context for one conversation, with the context cache in 16-bit unless noted. Fits leaves at least 20% of that memory for context; Tight leaves less.