MODEL / MISTRAL AI
Devstral Small 2 24B
The 256K maximum context is not a practical default on consumer memory.
1차 출처총 파라미터24B
추정 메모리~18.5 GBGGUF Q4 / BF16
컨텍스트256KText + Image
LicenseApache-2.0Multilingual
01 / 추천 용도
- coding agents
- repository work
- tool use
02 / 추정 적합도
03 / 배포 환경
OllamaEasy
ollama run <model-tag>llama.cppMedium
llama-server -m /path/to/verified-model.gguf --port 8080LM StudioEasy
Search “mistralai/Devstral-Small-2-24B-Instruct-2512” → Load a Q4/INT4 build → Start ServerMLX LMMedium
mlx_lm.chat --model mistralai/Devstral-Small-2-24B-Instruct-2512주의
The 256K maximum context is not a practical default on consumer memory.