The real cost to run Apertus 70B MeditronFO

EPFLiGHT · 70.6B parameters · 65.5K context · commercial OK

Apertus 70B MeditronFO — 70.6B params (EPFLiGHT). Auto-indexed from the Hugging Face Hub (16,962 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run Apertus 70B MeditronFO — $0 markup

On your own machine — $0. Runs free locally if you have about 54 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
On your own rented GPU — from $0.78/hr. 3× NVIDIA RTX 3090 24GB at the direct Vast.ai price (≈ $0.86 a session), $0 markup.
Via your own API key — $0.66/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	70.6B
Context window	65.5K tokens
Recommended quant	Q4_K_M
VRAM to run	~54 GB (at Q4_K_M, 16.4K context)
Download size	~42 GB
License	Commercial use OK

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

Related models

Meta Llama 3 70B — 70.6B, meta-llama
Meta Llama 3.1 70B Instruct quantized.w4a16 — 70.6B, RedHatAI
DeepSeek R1 Distill Llama 70B — 70.6B, deepseek-ai
Llama 3.1 70B — 70.6B, meta-llama
Meta Llama 3 70B Instruct — 70.6B, meta-llama

Browse: All models · Compare