Magistral Small 24B
Mistral’s reasoning model for mathematics, code and multilingual tool workflows. This artifact uses a 39K operating context rather than assuming the full architectural maximum.
Exact local Ollama manifest and configuration checked on 2026-10-20. Memory figures are conservative planning estimates; no DeviceTerra inference or speed test is claimed. Registry 39K context matches upstream recommended 40K operating limit. Official Mistral model card links both LM Studio and Ollama.
- Official model source
- Official engine artifact
Will it run?
MamiLens uses 30 GB as a conservative planning floor for this profile and its listed quantization. This is not measured speed. Processor, backend support, context length, memory bandwidth and other applications still affect the result.
Check your complete system →What is it useful for?
Suggested Ollama artifact
Confirm the tag on the official page before downloading, then run:
ollama run magistral:24bStart with a representative non-sensitive task. Record the exact runtime, quantization, context, load time, generation speed, memory use and answer quality.
Evidence and limits
Published context: 39K artifact maximum; practical context depends on memory. The source establishes specifications; it does not guarantee that maximum context fits at the MamiLens minimum RAM floor.