DeepSeek's MoE model with 552B total parameters and 8-16B active per token. 1M-token context, MIT license: free commercial use. Built for online serving, too large for local use on a single PC.
Back to resources
Models
NVIDIA Riva-Translate 4B Instruct v1.1
Released on Nov 19, 2026
NVIDIA's local translation model: 4.18B parameters in BF16 (~8.4 GB), a decoder-only Transformer pruned and distilled from Mistral-NeMo-Minitron-8B-Base. Translates across 12 languages and dialects (English, Chinese, Arabic, German, Spanish, French, Japanese, Korean, Russian, Portuguese); performance comparable to EuroLLM-9B-Instruct on FLORES and WMT24.
Features
Tags
Discover NVIDIA Riva-Translate 4B Instruct v1.1
Visit the official site to download, learn more and start using NVIDIA Riva-Translate 4B Instruct v1.1.
Related resources — Models
Models⚡
DeepSeek V4.1 Flash
Released Sep 10, 2026DeepSeek V4.1 Flash
LLMDeepSeekMoEOpen Source
Models⚡
FLUX.1 [dev]
Released Aug 1, 2024FLUX.2 [klein] 4B/9B
The most advanced open image model: excellent prompt adherence, solid anatomy, full fine-tuning. The standard for serious work.
ImmaginiDiffusionFLUX
Models⚡
FLUX.1 [schnell]
Released Aug 1, 2024FLUX.2 [klein] 4B/9B
Very few steps, high quality, and strong text rendering. The distilled FLUX variant, built for speed.
ImmaginiDiffusionFLUX

