HNHacker News🤖Qwen 3.8 27B available on Cerebras at 1500 tokens/sRanked #2 on Hacker News with 382 points and 118 comments.Browse all models available on Cerebras public endpoints.Will you change a model's architecture without notice?Where can I find your REAP pruned models?What are compression, quantization, and pruning?By altertable[1] Inference Docs[2] Hacker News discussion9/3/2026, 10:40:57 PM00000