Qwen 3.8 27B available on Cerebras at 1500 tokens/s

ModelsHow to Run Underdog Saluki 27B: 2-Bit Qwen3.8-27B Tool-Calling GuideOct 25

ModelsPrivacy-preserving inference on hosted models: a learned input-embedding transform for frozen Qwen3.8-27BOct 21

ModelsMeet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool CallingOct 9

ModelsMemStrata: 95% and 90.91% Source-Aware Accuracy on LongMemEval-500 and LoCoMo-1540 with a Local Qwen 3.8 27B Q4_K_M ReaderOct 6

Covered by 1 source