MODEL / MISTRAL AI
Devstral Small 2 24B
The 256K maximum context is not a practical default on consumer memory.
PrimärquelleGesamtparameter24B
Geschätzter Speicher~18.5 GBGGUF Q4 / BF16
Kontext256KText + Image
LicenseApache-2.0Multilingual
01 / GEEIGNET FÜR
- coding agents
- repository work
- tool use
02 / GESCHÄTZTE PASSFORM
03 / STARTEN MIT
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-2512Achtung
The 256K maximum context is not a practical default on consumer memory.