professorpalmer/bonsai-ada-surgery

Bonsai 2 27B: 262k context (trained max) on 12 GB, 54 to 97 tok/s decode, 2x prefill, q8_0 KV recipe, grammar tool calls 9/9. Same ternary weights. Windows bundle + receipts.

语言：Python · GitHub 星标：98 · Fork：6

话题：bonsai · cuda · llama-cpp · local-llm · quantization · qwen · rtx-4070 · speculative-decoding

在 GitHub 上查看原仓库