The real cost to run Hermes 4.3 36B

NousResearch · 36.2B parameters · 524.3K context · commercial OK

Hermes 4.3 36B — 36.2B params (NousResearch). Auto-indexed from the Hugging Face Hub (25,516 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run Hermes 4.3 36B — $0 markup

• On your own machine — $0. Runs free locally if you have about 27 GB of VRAM at Q4_K_M (point Spanvero at LM Studio, Ollama, or llama.cpp).
• On your own rented GPU — from $0.49/hr. NVIDIA RTX A6000 48GB at the direct RunPod price (≈ $0.45 a session), $0 markup.
• Via your own API key — $0.39/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

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

Related models

• Meta Llama 3 8B Instruct — 8B, NousResearch
• Meta Llama 3.1 8B Instruct — 8B, NousResearch
• Llama 2 7b hf — 6.7B, NousResearch
• Hermes 3 Llama 3.1 70B — 70.6B, NousResearch
• Llama 2 7b chat hf — 6.7B, NousResearch

Browse: More Nous Research models · All models · Compare

Spanvero · What's new · Prices as of 2026-06-22. We're an honest advisor — $0 markup, your own accounts, we never resell compute. © 2026 Cynosure LLC.