The real cost to run LFM2.5 1.2B JP 202606

LiquidAI · 1.2B parameters · 128K context · license restricted

LFM2.5 1.2B JP 202606 — 1.2B params (LiquidAI). Auto-indexed from the Hugging Face Hub (11,555 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run LFM2.5 1.2B JP 202606 — $0 markup

On your own machine — $0. Runs free locally if you have about 3 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
On your own rented GPU — from $0.26/hr. NVIDIA RTX 3090 24GB at the direct Vast.ai price (≈ $0.02 a session), $0 markup.
Via your own API key — $0.11/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	1.2B
Context window	128K tokens
Recommended quant	Q4_K_M
VRAM to run	~3 GB (at Q4_K_M, 16.4K context)
Download size	~1 GB
License	License restricted

Open the free Spanvero advisor → for the live, interactive math for your exact workload and hardware.

Related models

LFM2.5 1.2B Instruct — 1.2B, LiquidAI
LFM2 1.2B — 1.2B, LiquidAI
LFM2.5 8B A1B — 8.5B, LiquidAI
LFM2.5 350M — 400M, LiquidAI
LFM2.5 350M Base — 400M, LiquidAI

Browse: More Liquid AI models · All models · Compare