Skip to main content

Qwen 2.5 7B Instruct

Multilingual LLM with strong reasoning and instruction following.

Overview​

  • model_name: qwen-2.5-7b-instruct (curated base)
  • Source: Qwen/Qwen2.5-7B-Instruct
  • Scale: ~7B parameters
  • Served on: GPU via vLLM (transformers fallback)
  • Public endpoint: qwen-2.5-7b-instruct-public (task type chat, billed per request in USD)

When to use​

✅ Multilingual applications (strong on Chinese and English, good on others), multi-step reasoning, detailed Q&A, and complex instruction following.

❌ For fast/simple queries use Phi-3.5 Mini; for code use Qwen 2.5 Coder.

Live specs​

Context window, VRAM footprint, price, and readiness come from the live catalog — this page does not hardcode them:

curl "https://api.colabhive.com/api/builder/v1/endpoints?visibility=public&search=qwen-2.5-7b"

Quick start​

from colabhive import ColabHive

client = ColabHive(api_key="hive_...", account_id="YOUR_ACCOUNT_ID")

result = client.endpoints.infer(
    endpoint_id="qwen-2.5-7b-instruct-public",   # SDK resolves the name to a UUID
    input_data={"messages": [{"role": "user", "content": "Explain quantum entanglement."}]},
    max_tokens=500,
    temperature=0.7,
)

# Sync by default; a "queued" status means poll GET /tasks/{task_id}
print(result["result"] if result.get("status") != "queued"
      else client.endpoints.get_task(result["task_id"]))

The same model is also reachable through the OpenAI-compatible /v1/chat/completions surface, addressed by model name or endpoint UUID.

Tips​

  • Ask for step-by-step reasoning on hard problems.
  • For non-English tasks, Qwen is a strong choice without a separate translation step.

Next steps​

Authors: José Luis Minich, Maximiliano Lucius.