Text-only ROCmFPX/ROCmFP4 GGUF builds of nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451, with the checkpoint’s embedded one-layer MTP draft model preserved. These are experimental AMD Strix Halo builds. The custom ROCmFPX tensor types require charlie12345/ROCmFPX; they will not load in an unmodified stock llama.cpp build. All three files retain 64 main transformer blocks plus the embedded blk.64 MTP block. The source checkpoint’s vision tensors were intentionally omitted; these GGUFs are for text generation. This is the current text-only llama.cpp router preset used on a 128 GB Strix Halo system. It gives one slot the full native 262,144-token context, uses F16 KV, enables cross-turn checkpoint reuse, and runs the embedded MTP head with nmax=5. The chat template is froggeric’s chattemplate.jinja` v21.3. Download it separately and replace the example paths below. cache-ram = 65536 and F16 KV are intentionally memory-hungry settings for a 128 GB unified-memory machine. Reduce the reuse-cache ceiling and/or use Q8 KV on smaller systems. Temperature 0.6 is the precise/coding profile; 1.0 is a useful starting point for general or creative work. — Native 262,144-token context…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: vmlinux
Теги: llama.cpp, gguf, qwen3.6, rocmfpx, rocmfp4, mtp, vulkan, strix-halo
Лайков: 4 | Загрузок: 303
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
