This repo contains three experimental IQ1M` GGUF quants derived from REAP-pruned Qwen 3.6 35B A3B checkpoints. I just wanted to get a local LLM that could answer the car wash test correctly on my iPad Pro with 8GB RAM as all the other smaller LLMs it could run just couldn’t, and also faster than 3tk/s for the full 35B IQ1M model due to partial offload to swap. These are not plain base-model quants. They come from REAP-pruned MoE checkpoints, then were converted to trunk-only GGUF and quantized with a Bartowski-style Qwen 3.6 IQ1M` tensor policy. Quantization method: — GGUF export — trunk-only / no-mtp conversion path — fresh per-model imatrix — Bartowski-style Qwen 3.6 IQ1M` tensor map — Use qwen3.6-35b-reap25iq1m.gguf if you want the strongest general-purpose REAP variant. — Use qwen3.6-35b-reap40iq1m.gguf if you care more about instruction-following and strict prompt obedience. — Use qwen3.6-35b-reap50iq1m.gguf` only if size is the main priority. — reap25 is the strongest broad-quality REAP quant. — reap40 is the most interesting instruction-following variant. It gives up a lot on HellaSwag, but beats reap25 and reap50 on both strict IFEval metrics. — reap50 is the most…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: dxx117
Теги: llama.cpp, gguf, qwen3.6, moe, quantization, reap, iq1_m, en
Лайков: 3 | Загрузок: 54
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
