The real cost to run Mellum2 12B A2.5B Thinking

JetBrains · 12.1B parameters · 131.1K context · commercial OK

Mellum2 12B A2.5B Thinking — 12.1B params (JetBrains). Auto-indexed from the Hugging Face Hub (25,831 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run Mellum2 12B A2.5B Thinking — $0 markup

On your own machine — $0. Runs free locally if you have about 9 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 (≈ $0.14 a session), $0 markup.
Via your own API key — $0.20/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	12.1B
Context window	131.1K tokens
Recommended quant	Q4_K_M
VRAM to run	~9 GB (at Q4_K_M, 16.4K context)
Download size	~7 GB
License	Commercial use OK

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

Related models

Mellum2 12B A2.5B Base — 12.1B, JetBrains
Gemma 3 12B — 12B, Google
Gemma 4 12B OBLITERATED — 12B, OBLITERATUS
MN 12B Mag Mell R1 — 12.2B, inflatebot
NVIDIA Nemotron Nano 12B v2 — 12.3B, nvidia

Browse: All models · Compare