Qwen2.5 72B Instruct AWQ
Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.
$ curl https://hostyourai.com/api/v1/chat/completions \
-H "Authorization: Bearer hyai-..." \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen2.5-72B-Instruct-AWQ",
"messages": [{"role": "user", "content": "Hello!"}]
}'
Call it now
Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.
text->text · qwen · sovereign EU
Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain
Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters.
- Router
- Router · on request
- Dedicated
- Dedicated · available
Specifications
| Parameters | 72B |
|---|---|
| Context window | 32,768 tokens |
| Minimum VRAM | 345 GB |
| Architecture | Qwen2ForCausalLM (vLLM) |
| License | open-weights |
| Modality | text->text |
| Released | September 2024 |
| Publisher | qwen ↗ |
Pricing
Shared router · per token
Dedicated GPU · per hour
Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.
✓ Verified working on 06-07-2026, responded in 2185 ms on our EU infrastructure.
Bench index
Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.
Translated from its LiveBench result onto the same scale.
Range 49.2 to 63.5
Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 19-11-2026
LiveBench · 52.9
LiveBench · All tasks
| web of lies v2 | 60.0 |
|---|---|
| zebra puzzle | 34.0 |
| spatial | 44.0 |
| LCB generation | 55.1 |
|---|---|
| coding completion | 58.0 |
| AMPS Hard | 63.0 |
|---|---|
| math comp | 52.1 |
| olympiad | 42.0 |
| cta | 52.0 |
|---|---|
| tablejoin | 36.4 |
| tablereformat | 58.0 |
| connections | 36.5 |
|---|---|
| plot unscrambling | 35.9 |
| typos | 42.0 |
| paraphrase | 71.9 |
|---|---|
| simplify | 72.6 |
| story generation | 83.9 |
| summarize | 73.6 |
Frequently asked questions
Can I run Qwen2.5 72B Instruct AWQ in the EU?
Yes. HostYourAI runs Qwen2.5 72B Instruct AWQ on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.
Is hosting Qwen2.5 72B Instruct AWQ GDPR-compliant?
Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.
How much does Qwen2.5 72B Instruct AWQ cost?
Qwen2.5 72B Instruct AWQ needs several GPUs at once, so it runs as a dedicated deployment billed per GPU minute rather than per token. Tell us your volume and we will work it out with you.
Is the API OpenAI-compatible?
Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.
More models from Qwen
One platform, four layers
Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.
Try Qwen2.5 72B Instruct AWQ for free
Creating an account takes a minute. Test Qwen2.5 72B Instruct AWQ straight away in the playground.







