ModelRigSYS: READY
Home / Models / Mistral Small 24B
LLM / MODEL FILE

Mistral Small 24B

Mistral model for mid-size general assistant. Memory figures are estimates, not measured benchmarks.

Parameters24.0B
Q4 estimate18.3 GB
WorkloadLLM
Best proofTest exact runtime
QUANTIZATION

Memory scenarios

CLOSEST FITS

Hardware near the Q4 line

LIMITFitting in memory does not guarantee acceptable speed.

Runtime, drivers, memory bandwidth, context, batch size, offloading, and model architecture all matter.