Two open-weights releases: Victoria (Qwen3.8-Flash-Next with 44% of experts cut, 70% Terminal-Bench 2.1, GGUF included) and Maple (a Canada-first fine-tune)
英文标题：Two open-weights releases: Victoria (Qwen3.8-Flash-Next with 44% of experts cut, 70% Terminal-Bench 2.1, GGUF included) and Maple (a Canada-first fine-tune)
We had a Dell B300 in the lab for a few weeks and used it to create two fine tunes of Qwen Flash Next. Victoria (coding and agents) Qwen3.8-Flash-Next cut down by 44% using a paper / technique called REAP: 512 down to 288 per layer. Retrained at 4-bit (NVFP4) afterwards, so it's trained for the for
中文
We had a Dell B300 in the lab for a few weeks and used it to create two fine tunes of Qwen Flash Next. Victoria (coding and agents) Qwen3.8-Flash-Next cut down by 44% using a paper / technique called REAP: 512 down to 288 per layer. Retrained at 4-bit (NVFP4) afterwards, so it's trained for the for
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
We had a Dell B300 in the lab for a few weeks and used it to create two fine tunes of Qwen Flash Next. Victoria (coding and agents) Qwen3.8-Flash-Next cut down by 44% using a paper / technique called REAP: 512 down to 288 per layer. Retrained at 4-bit (NVFP4) afterwards, so it's trained for the for