Qwen-AgentWorld-35B-A3B-bf16
Full-precision (bfloat16) MLX build of Qwen/Qwen-AgentWorld-35B-A3B. The original weights load in mlx-lm / oMLX as-is — this repo...
Full-precision (bfloat16) MLX build of Qwen/Qwen-AgentWorld-35B-A3B. The original weights load in mlx-lm / oMLX as-is — this repo...
This model was converted to GGUF format from huihui-ai/Huihui-Qwen-AgentWorld-35B-A3B-abliterated using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4 is a GPTQ-quantized checkpoint intended for efficient GPU inference, published by groxaxo. It is intended for open-source...
BF16 Attention FP8 MLP Experts (except the first mlp layer due to huge quantization error) Detailed quantization error...
🌐 Website: https://ui-simulator.notion.site/llms-as-scalable-digital-world-simulator This is the agent trained on retrieval-augmented web UI-Simulator. It is trained to solve WebArena...
Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. 📑 Technical Report | 📖 Blog |...
This model was converted to GGUF format from Qwen/Qwen-AgentWorld-35B-A3B using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
Официальная сборка OsaurusAI MXFP8 Qwen/Qwen-AgentWorld-35B-A3B (Apache-2.0) — гибридный MoE ~35B / ~3B (qwen35moe). 8-битный микромасштабируемый FP практически без...
oQ4 (смешанная точность на основе данных, ≈4,6 бит в секунду) MLX-квантование Qwen/Qwen-AgentWorld-35B-A3B, созданное с помощью quantizeoqstreaming oMLX. Для...
Этот адаптер LoRA добавляет в Qwen/Qwen3-4B-Thinking-2507 возможности осведомленности о выполнении. Вдохновленный исследованием Meta CWM (Code World Model), он...