Ministral-3-14B-Instruct-2512-NVFP4
— Архитектура модели: MistralForCausalLM — Вход: Текст — Выход: Текст — Оптимизация модели: — Квантование веса: FP4 —...
— Архитектура модели: MistralForCausalLM — Вход: Текст — Выход: Текст — Оптимизация модели: — Квантование веса: FP4 —...
— Model Architecture: Qwen3ForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: INT4 —...
— Verifier: meta-llama/Llama-3.1-8B-Instruct — Speculative Decoding Algorithm: EAGLE-3 — Model Architecture: Eagle3Speculator — Release Date: 07/27/2025 — Version:...
— Model Architecture: Qwen3MoeForCausalLM — Input: Text — Output: Text — Model Optimizations: — Activation quantization: FP8 —...
— Model Architecture: Qwen3ForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: INT4 —...
— Model Architecture: Phi3ForCausalLM — Input: Text — Output: Text — Model Optimizations: — Activation quantization: FP8 —...
— Verifier: openai/gpt-oss-120b — Speculative Decoding Algorithm: EAGLE-3 — Model Architecture: Eagle3Speculator — Release Date: 03/10/2026 — Version:...
— Model Architecture: Qwen3NextForCausalLM — Input: Text — Output: Text — Model Optimizations: — Weight quantization: INT4 —...
— Model Architecture: MistralForCausalLM — Input: Text — Output: Text — Model Optimizations: — Activation quantization: FP8 —...
— Model Architecture: Qwen3ForCausalLM — Input: Text — Output: Text — Model Optimizations: — Activation quantization: FP8 —...