OSAIM
Open Source AI Models

Alibaba

Qwen

Alibaba's Qwen series. Qwen2.5 delivers competitive frontier-class performance across sizes from 0.5B to 72B with permissive licensing.

Visit homepage ↗

History & context

Alibaba's Qwen ('通义千问' / Tongyi Qianwen) family quickly became the strongest non-Meta open-weights family. Qwen2 (June 2024) delivered competitive quality at the 7B and 72B sizes. Qwen2.5 (September 2024) was the breakthrough — across sizes from 0.5B to 72B, with specialised variants for code and math.

Qwen2.5 sub-72B sizes are released under Apache 2.0 with no usage cap, which makes them the most permissively-licensed strong-quality models available. The 72B uses the Qwen License (100M MAU cap, similar to Llama's pattern).

Qwen2.5 Coder 32B (November 2024) reached GPT-4o-class HumanEval scores at a size that fits on a single H100. QwQ 32B Preview (also November 2024) was Alibaba's first reasoning-focused 'thinking' model.

Flagship model

6 models in this family

Qwen2.5 72B Instruct
72B

The flagship Qwen 2.5 release. Competes with Llama 3.1 405B on many benchmarks at one-fifth the parameter count. Note the 72B specifically uses the Qwen License (commercial use up to 100M MAU) — the smaller Qwen2.5 sizes are Apache 2.0.

Context
128K
License
qwen
VRAM Q4
43.2 GB
Qwen2.5 32B Instruct
32B

32B sweet-spot model: strong reasoning, fits on one H100 in fp16, on a 4090 at Q4. The 32B size in particular hits a quality/cost knee — quality scales with parameters faster than cost up to ~32B, and slower afterwards. Favoured for production chat where 7B isn't sharp enough and where 70B+ would over-spec the hardware budget. Apache 2.0 licence.

Context
128K
License
apache-2-0
VRAM Q4
19.2 GB
Qwen2.5 Coder 32B
32B

Coding-specialised Qwen2.5 32B fine-tune. GPT-4o-class on HumanEval and BigCodeBench at the time of release. Trained on additional code-heavy data with extended pre-training. Apache 2.0. Natural pick for self-hosted coding assistants, code-review automation, and any agent loop that primarily writes code.

Context
128K
License
apache-2-0
VRAM Q4
19.2 GB
QwQ 32B Preview
32B

Qwen's reasoning-focused 'thinking' model. Generates long chains-of-thought before answering, similar to OpenAI's o1 and DeepSeek R1 lineage. Optimised for math and competition-style problem solving. The Preview tag means Qwen is iterating quickly; later versions may obsolete this one. Useful today for math-heavy workloads where a slow, careful answer is preferred to a fast wrong one.

Context
33K
License
apache-2-0
VRAM Q4
19.2 GB
Qwen2.5 14B Instruct
14B

Mid-size Qwen2.5 with broad task coverage. The sweet spot for users who want noticeably better quality than 7B but can't justify the hardware footprint of 32B or 72B.

Context
128K
License
apache-2-0
VRAM Q4
8.4 GB
Qwen2.5 7B Instruct
7B

Apache-2.0-licensed 7B model with surprisingly strong reasoning and multilingual chops. Qwen 2.5 trains on a larger and more carefully filtered corpus than the original Qwen series, and the 7B variant punches well above its weight on coding and math benchmarks. A strong default for cost-sensitive chat workloads and for fine-tuning experiments where the Apache licence simplifies downstream redistribution.

Context
128K
License
apache-2-0
VRAM Q4
4.2 GB
Comparing Qwen against another family? Try the side-by-side comparator or browse all leaderboards.