QwQ-32B Preview
Alibaba's first open-weight reasoning model, released November 2024 as a "preview." Used the same RL-on-reasoning-traces recipe OpenAI used for o1, but with the model weights downloadable — making it the first time anyone outside the frontier US labs could study how reasoning capability is trained in. Its release 8 weeks before DeepSeek R1 partly set the expectation that "open reasoning" would arrive within months, not years.
How are Intelligence, Speed & Cost bucketed?
- Top 1%≤ 1%
- Top 5%≤ 5%
- Top 10%≤ 10%
- Good≤ 25%
- Medium≤ 50%
- Below avg> 50%
- Top 1%≥ 345 tok/s
- Top 5%≥ 237 tok/s
- Top 10%≥ 196 tok/s
- Good≥ 146 tok/s
- Medium≥ 90 tok/s
- Slow< 90 tok/s
- Freeopen weights · self-host
- Low< $1 / M out
- Moderate$1–5 / M out
- High≥ $5 / M out
Why it matters
QwQ proved that the o1 recipe was reproducible from public research alone — no OpenAI insider knowledge required. That proof, more than the model's specific capabilities, was the contribution. By Q1 2025, ten different labs had released reasoning models; the technique had become a shared methodology.
Core Capabilities
Context Window
Availability
Pricing Model
Capability / Performance
Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).
What it feels like
- Language model from Alibaba — see the linked sources below for benchmark and review coverage
- Tool-use and agent loops are the typical fit per the published model card
Best use cases
- Agent / tool-use workflows that match the model's published benchmarks
- See the model spec and sources block for benchmarked use cases
Tools to try
Not ideal for
- Tasks far outside the modalities listed in this model's spec
- Workflows where a more recent successor in the same family scores higher