ModelRigSYS: READY
Home / Models / DeepSeek-R1 Distill Qwen 7B
LLM / MODEL FILE

DeepSeek-R1 Distill Qwen 7B

DeepSeek model for compact distilled reasoning. Memory figures are estimates, not measured benchmarks.

Parameters7.6B
Q4 estimate6.8 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.