Models to evaluate
| Model | Architecture / size | License | Hardware class | Provider |
|---|---|---|---|---|
| Qwen3 8BQwen / Alibaba | 8B · local general-purpose model | Apache 2.0 | ≤8B · consumer/local | 🇨🇳 China |
| Qwen3-32BQwen / Alibaba | 32B · dense | Apache 2.0 | 17–32B · high-memory workstation | 🇨🇳 China |
| Qwen3-Coder-30B-A3B-InstructQwen / Alibaba | 30B / ~3B active · coding MoE | Apache 2.0 | 17–32B · high-memory workstation | 🇨🇳 China |
| Qwen3-VL-30B-A3B-InstructQwen / Alibaba | 30B-class sparse vision-language model | Apache 2.0 | 17–32B · high-memory workstation | 🇨🇳 China |
| Ministral 3 8B Instruct 2512Mistral AI | 8B-class · vision-language edge model | Apache 2.0 | ≤8B · consumer/local | 🇫🇷 France |
| Devstral Small 2 24B Instruct 2512Mistral AI | 24B · coding agent model | Apache 2.0 | 17–32B · high-memory workstation | 🇫🇷 France |
| Mistral Small 4 119B A6BMistral AI | 119B / 6.5B active · multimodal MoE | Apache 2.0 | Model-specific · large / specialized | 🇫🇷 France |
| Magistral Small 2506Mistral AI | 24B-class · reasoning | Apache 2.0 | 17–32B · high-memory workstation | 🇫🇷 France |
Decision criteria
Match checkpoint to workload before comparing families.
Compare dense, MoE and multimodal architectures separately.
Provider origin differs, but deployment location is chosen by the deployer.
Verify the exact checkpoint license; family labels do not guarantee identical terms.
Deployment reality
Validate the exact checkpoint, precision or quantization, runtime, context length and concurrency target. Weight memory alone does not capture KV cache, runtime workspaces, multimodal encoders or distributed-serving overhead.
OWM keeps license, provider origin and data residency separate. A provider-country label is provenance metadata; the deployer determines where inference and connected services run.