Full-precision (bfloat16) MLX build of Qwen/Qwen-AgentWorld-35B-A3B. The original weights load in mlx-lm / oMLX as-is — this repo packages them for Apple Silicon without any precision loss. For Apple Silicon. Runs in mlx-lm, oMLX, or any MLX app. Quantized siblings: oQ4 (≈4.6 bpw, ≈19 GB) and oQ3.5 (≈3.5 bpw, ≈16 GB). — Text-only. The checkpoint declares a visionconfig and MTP heads in config.json, but ships no vision or mtp. weights (693 tensors, 0 vision, 0 MTP) — both are vestigial skeleton inherited from the Qwen3.5 base, and languagemodelonly: true makes it a pure LM. Nothing multimodal is present to use. — ≈65 GB** on disk; peak memory ≈69 GB generating. Fits in 128 GB unified memory; use a quantized sibling on smaller machines. Measured with oMLX (Auto engine) on a Macbook Pro M5 Max 128GB 40 GPU. Single request: For ≈1.8× the single-request decode throughput at ≈⅓ the memory, see the oQ4 sibling. The model uses thinking mode (…) by default. Recommended sampling: temperature=0.6, topp=0.95, topk=20. See the base model card for the seven agent domains and domain-specific system prompts.
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: mlx-community
Теги: mlx, qwen3_5_moe, qwen, world-model, agent, environment-simulation, conversational
Лайков: 3 | Загрузок: 77
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
