DeepSeek-V4-Flash-0731-NVFP4
NVFP4 маршрутизируемое экспертное квантование deepseek-ai/DeepSeek-V4-Flash-0731, полученное с помощью собственного опубликованного потока NVIDIA Model-Optimizerdeepseekv4 `(modelopt 0.45.0). На момент публикации...
NVFP4 маршрутизируемое экспертное квантование deepseek-ai/DeepSeek-V4-Flash-0731, полученное с помощью собственного опубликованного потока NVIDIA Model-Optimizerdeepseekv4 `(modelopt 0.45.0). На момент публикации...
FP8 W8A8 (dynamic per-token activations) quantization of Nanbeige/Nanbeige4.2-3B — the looped transformer (22 layers × numloops: 2). 4.9...
Quality-first mixed-precision ModelOpt quantization of poolside/Laguna-S-2.1, exported directly from Poolside’s BF16 checkpoint. This is a serving-oriented checkpoint, not...
A load-and-go FP8 quantization of google/gemma-4-12B-it, plus a reproducible recipe for running it with DeepSeek DSpark speculative decoding...
A high-efficiency FP8-quantized Mixture-of-Experts model fine-tuned and optimized for coding, software engineering, and agentic development workflows. It is...
> [!WARNING] > This model is a beta preview and a research artifact. It is not an open...
We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models — DeepSeek-V4-Pro with...
FP8 quantized version of google/gemma-4-12B-it (12B params, unified multimodal model). Produced and maintained by vrfai. This model was...
Эта крошечная модель предназначена для отладки. Произвольно инициализируется с помощью конфигурации, адаптированной из deepseek-ai/DeepSeek-V4-Pro. — safetensors: 0.8.0 —...
This is a PrismaQuant 4.75-bit mixed-native quantization of mistralai/Mistral-Medium-3.5-128B, exported for vLLM using the compressed-tensors format. This artifact...