Mistral
European open-weight model family known for efficiency at small parameter counts.
Обзор
Mistral is an open-weight model family that emphasises quality per parameter rather than raw size, so a small model can run on modest hardware without collapsing in quality. It solves the cost problem for teams whose workload is not hard enough to justify a frontier model. It exists because most production tasks are narrow enough that a well-trained small model is sufficient, and serving one is an order of magnitude cheaper than calling a large hosted model.
Граф технологий
Как Mistral связана с остальным стеком.
Использует и зависит от
- Transformer architecture Algorithms Mistral based on Transformer High ✓ source
Применяется к
- LoRA technique Techniques LoRA used for Mistral High ✓ source
- Ollama tool Infrastructure Ollama used for Mistral High ✓ source
- Quantization technique Techniques Quantization used for Mistral High ✓ source
- llama.cpp tool Infrastructure llama.cpp used for Mistral High ✓ source
- vLLM tool Infrastructure vLLM used for Mistral High ✓ source
Инструменты
ПО, которое реализует Mistral или интегрируется с ним.
LLM Frameworks
Альтернативы
Сравнения
Подробные сопоставления с альтернативами выше.