Qwen3-VL-235B-A22B-Instruct-FP8-block
— Model Architecture: Qwen3VLMoeForConditionalGeneration — Input: Text/Image/Video — Output: Text — Model Optimizations: — Weight quantization: FP8 —...
— Model Architecture: Qwen3VLMoeForConditionalGeneration — Input: Text/Image/Video — Output: Text — Model Optimizations: — Weight quantization: FP8 —...
Web Chat: https://chat.dphn.ai Telegram bot: https://t.me/DolphinAI_bot — Lium — provided on-demand 8x H200s for testing and evaluation. —...
Today, we’re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but...
Qwen3-Coder доступен в нескольких размерах. Сегодня мы рады представить Qwen3-Coder-30B-A3B-Instruct. Эта оптимизированная модель поддерживает впечатляющую производительность и эффективность,...
W4A16 (4-bit weights, 16-bit activations) quantized version of Qwen/Qwen3-30B-A3B-Thinking-2507 using LLM-Compressor. — 🗜️ Memory: ~75% reduction vs FP16...
W8A8 (8-bit weights and activations) quantized version of Qwen/Qwen3-Coder-30B-A3B-Instruct using LLM-Compressor. — 🗜️ Memory: ~50% reduction vs FP16...
W8A8 (8-bit weights and activations) quantized version of Qwen/Qwen3-30B-A3B-Thinking-2507 using LLM-Compressor. — 🗜️ Memory: ~50% reduction vs FP16...
🤗 HuggingFace | 🤖 ModelScope | 🪡 AngelSlim 🖥️ Official Website | 🕖 HunyuanAPI | 🕹️ Demo Hunyuan is Tencent’s open-source efficient large language model series, designed for...
Jan-Nano is a compact 4-billion parameter language model specifically designed and trained for deep research tasks. This model...
This model was obtained by quantizing the weights of deepseek-ai/DeepSeek-V3-0324 to INT4 data type. This optimization reduces the...