The real cost to run Tongyi DeepResearch 30B A3B

Alibaba-NLP · 30.5B parameters · 131.1K context · commercial OK

Tongyi DeepResearch 30B A3B — 30.5B params (Alibaba-NLP). Auto-indexed from the Hugging Face Hub (105,709 downloads). Parameter count is exact; download size and quantizations are estimates.

What it costs to run Tongyi DeepResearch 30B A3B — $0 markup

On your own machine — $0. Runs free locally if you have about 22 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 (≈ $0.37 a session), $0 markup.
Via your own API key — $0.34/1M tokens (blended input + output). No GPU to manage (rough estimate for this size).

Key facts

Parameters	30.5B
Context window	131.1K tokens
Recommended quant	Q4_K_M
VRAM to run	~22 GB (at Q4_K_M, 16.4K context)
Download size	~18 GB
License	Commercial use OK

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

Related models

Qwen3 30B A3B — 30.5B, Qwen
Qwen3 Coder 30B A3B Instruct — 30.5B, Qwen
Qwen3 30B A3B Instruct 2507 — 30.5B, Qwen
Qwen3 30B A3B abliterated — 30.5B, mlabonne
Qwen3 30B A3B Thinking 2507 — 30.5B, Qwen

Browse: All models · Compare