6arXiv cs.CL (Computation and Language)·
Soofi S 30B-A3B: Sovereign German-English MoE Hybrid Mamba Transformer Released Open-Source
Researchers present Soofi S 30B-A3B, a Mixture-of-Experts hybrid Mamba Transformer foundation model for German and English, activating only 3B of 30B parameters per token with near-constant inference cache for long-context efficiency. Pretrained on ~27 trillion tokens with up-weighted German data, it claims top aggregate scores among fully open models in both languages, outperforming OLMo 3 32B and Apertus 70B, and surpasses all European sovereign baselines tested. The model was built on Deutsche Telekom's sovereign HPC infrastructure in Munich and will be released with weights, checkpoints, hyperparameters, training code, and full data accounting under permissive terms.
Related guides (3)
Related events (8)
Mixtral 8x7B: Mistral AI Releases Sparse Mixture-of-Experts Open-Weight Model
Mistral AI has released Mixtral 8x7B, a sparse mixture-of-experts (SMoE) model with 46.7B total parameters but only 12.9B active parameters per token, enabling inference speed and cost equivalent to a 12.9B model. Licensed under Apache 2.0, Mixtral outperforms Llama 2 70B on most benchmarks and matches or exceeds GPT-3.5, with support for 32k context, five European languages, and strong code generation. An instruction-tuned variant (Mixtral 8x7B Instruct) achieves 8.3 on MT-Bench, claimed best among open-source models at release. The model is deployed behind Mistral's mistral-small API endpoint and supported via vLLM with Megablocks CUDA kernels.
Nemotron-Labs Audex-30B: Unified audio-text MoE LLM with no text regression
Nvidia's Nemotron Labs introduces Audex-30B-A3B, a 30B-parameter mixture-of-experts audio-text LLM built on the Nemotron-Cascade-2 text backbone. The model handles audio understanding, ASR, translation, TTS, and speech-to-speech generation within a single Transformer decoder by projecting audio into the text embedding space. Training used 157.4B audio tokens and 320.5B text tokens with multi-stage supervised learning, RL, and on-policy distillation. Model checkpoints are publicly released, and the authors report state-of-the-art audio performance with minimal regression on text reasoning and agentic capabilities.
Mistral Small 4: Unified Multimodal, Reasoning, and Coding MoE Model Released Under Apache 2.0
Mistral AI has released Mistral Small 4, a 119B-parameter Mixture-of-Experts model (6B active per token) that unifies capabilities previously split across Magistral (reasoning), Pixtral (multimodal), and Devstral (coding agents) into a single open-weights model. The model features a 256k context window, configurable reasoning effort via a `reasoning_effort` parameter, native text and image input support, and is released under Apache 2.0. Mistral claims 40% latency reduction and 3x throughput improvement over Mistral Small 3, with benchmark results showing competitive performance against GPT-OSS 120B and Qwen models while producing significantly shorter outputs. The release includes day-0 availability as an NVIDIA NIM and support across vLLM, llama.cpp, SGLang, and Transformers.
Codestral Mamba: Mistral AI Releases Apache 2.0 Mamba-Architecture Code Model
Mistral AI has released Codestral Mamba, a 7.3B-parameter code-focused language model built on the Mamba state-space architecture rather than the Transformer architecture. The model offers linear-time inference and theoretically infinite sequence length, tested up to 256k tokens in-context retrieval. Developed with Mamba co-creators Albert Gu and Tri Dao, it is released under Apache 2.0 and available via HuggingFace, mistral-inference SDK, TensorRT-LLM, and Mistral's la Plateforme API. Mistral positions it as a local code assistant that performs on par with state-of-the-art transformer-based code models.
Mistral AI Releases Mixtral 8x22B Under Apache 2.0
Mistral AI has released Mixtral 8x22B, a sparse Mixture-of-Experts model with 141B total parameters but only 39B active parameters, under the permissive Apache 2.0 license. The model features a 64K token context window, native function calling, multilingual support across five European languages, and strong math and coding performance. Mistral claims it outperforms all other open-weight models on standard benchmarks while being faster than dense 70B models due to sparse activation. An instructed version achieves 90.8% on GSM8K maj@8.
Mixture of Experts (MoEs) in Transformers
A Hugging Face blog post covering Mixture of Experts (MoE) architectures as applied to transformer models. The post likely explains the technical foundations, training considerations, and practical deployment aspects of MoE models. Given the timing in early 2026, it likely contextualizes recent MoE-based frontier models and tooling support within the Hugging Face ecosystem.
Nvidia Nemotron 3 Ultra: hybrid Mamba-transformer open-weights model targeting agentic workloads
Nvidia released Nemotron 3 Ultra, a 550B parameter (55B active) hybrid Mamba-transformer mixture-of-experts model with a 1M token context window, publishing weights, training data, and RL environments under an open license. The model ranks as the highest-scoring U.S. open-weights model on the Artificial Analysis Intelligence Index (47.7-48.2) and is approximately three times faster than comparable open-weights rivals, though it trails leading Chinese models like Kimi K2.6 and DeepSeek V4 Pro on intelligence benchmarks. Nvidia used a novel Multi-Teacher On-Policy Distillation approach with 10+ specialized teacher models and trained using NVFP4 quantization. The release is strategically motivated by Nvidia's interest in a healthy open-weights ecosystem that drives AI semiconductor adoption.
Falcon Mamba: First Strong Attention-Free 7B Model
Technology Innovation Institute (TII) releases Falcon Mamba, a 7B parameter state space model (SSM) based on the Mamba architecture, announced as the first attention-free model at this scale to match or exceed transformer-based models on standard benchmarks. The model is hosted on Hugging Face and represents a significant milestone for SSM-based architectures competing with transformers. This release advances the case for pure SSM models as viable alternatives to attention-based LLMs at the 7B scale.