Atlas

Models

← All models

QwQ 32B ArliAI RpR v1

ArliAI · 2025-04-07 · 32.8B parameters

QwQ-32B-ArliAI-RpR-v1 is ArliAI's Apache-2.0 open-weight fine-tune of Qwen/QwQ-32B for role-play and creative writing with multi-turn reasoning. Its model card lists a 128K-token maximum context while noting 32K as the realistic range.

Benchmark scores

BenchmarkScore
SnakeBench Average Apples0.5
SnakeBench Best Apples2.0
SnakeBench Rating24.6
SnakeBench Total Apples14.0
SnakeBench Win Rate58.3
Loading Atlas data…