community pool / model answer

UncensoredLM-DeepSeek-R1-Distill-Qwen-14B

chat · uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B

27 tok/s · model median · 1 runs in the model record.

Reference rigQuantizationMedian resultBasisTTFT (ms)Peak VRAMMax contextEngines
RTX 5000 16GB4-bit27 tok/sreported-15.4 GB65,536llama.cpp

Context tested

The table above is the tested context for each exact rig and quantization cell. Empty fields remain empty rather than being filled with an estimate.