Opt.Gear Technical Report

• URL: http://arxiv.org/abs/2608.01034v2
• Date: Tue, 04 Aug 2026 01:57:33 GMT
• Title: Opt.Gear Technical Report
• Abstract summary: OptGear is a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability.<n>It includes a dense model (1M, 270M, and 1B) with a context length of 64K.<n>OptGear-1M is the first generative language model to achieve 20 TPS with W4A32 quantization on the ARM Cortex-M7 CPU.
• Score: 3.573729952898132
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce OptGear, a foundation model designed for efficient on-device deployment, real-tim inference, and strong task capability. It includes a dense model (1M, 270M, and 1B) with a context length of 64K. We designed a new hybrid architecture that combines a convolutional key-value gated mixer with local-global attention to reduce the KV-cache memory that tends to increase exponentially with long context. This architecture delivers up to X4.9 faster prefill and decoding speeds on the NPUs compared to models of a similar scale models. From a 2T tokens candidate corpus, OptGear is trained on a curated 0.5T tokens subset without knowledge distillation. This is the most data-efficient of the existing foundation models. All models are released with open weights and deployment binaries for ONNX, Qualcomm NPU, and Apple ANE making OptGear a practical base for edge applications that need fast, memory-efficient inference and strong task capabilities. Furthermore, to expand the ecosystem of on-device generative language models, we are introducing the OptGear-1M that can be deployed on Micro-Controller Units (MCUs), a Tiny Language Model (TLM). OptGear-1M is the first generative language model to achieve 20 TPS with W4A32 quantization on the ARM Cortex-M7 CPU of the STM32H747I-DISCO.

Related papers

• Scalable Training of Mixture-of-Experts Models with Megatron Core [26.9162079065285]
  Scaling Mixture-of-Experts (MoE) training introduces systems challenges absent in dense models.<n>Because each token activates only a subset of experts, this sparsity allows total parameters to grow much faster than per-token computation.<n>We address these challenges for MoE training through integrated optimizations spanning memory (fine-dimensional recomputation, offloading), communication, and computation.
  arXiv  Detail & Related papers  (2026-03-08T15:42:43Z)
• MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling [80.48332380100915]
  MiniCPM-SALA is a hybrid model that integrates the high-fidelity long-context modeling of sparse attention with the global efficiency of linear attention.<n>On a single NVIDIA A6000D GPU, the model achieves up to 3.5x the inference speed of the full-attention model at the sequence length of 256K tokens.
  arXiv  Detail & Related papers  (2026-02-12T09:37:05Z)
• E-MMDiT: Revisiting Multimodal Diffusion Transformer Design for Fast Image Synthesis under Limited Resources [12.244453688491731]
  Efficient Multimodal Diffusion Transformer (E-MMDiT) is an efficient and lightweight multimodal diffusion model with only 304M parameters for fast image synthesis.<n>Our model for 512px generation, trained with only 25M public data in 1.5 days on a single node of 8 AMD MI300X GPUs, achieves 0.66 on GenEval and easily reaches to 0.72 with some post-training techniques such as GRPO.
  arXiv  Detail & Related papers  (2025-10-31T03:13:08Z)
• dInfer: An Efficient Inference Framework for Diffusion Language Models [54.80918957287927]
  Diffusion-based large language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs.<n>We present dInfer, an efficient and framework for dLLM inference.
  arXiv  Detail & Related papers  (2025-10-09T16:19:42Z)
• MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe [68.04078852416248]
  MiniCPM-V 4.5 is an 8B parameter model designed for high efficiency and strong performance.<n>We introduce three core improvements in model architecture, data strategy and training method.<n>MiniCPM-V 4.5 achieves state-of-the-art performance among models under 30B size.
  arXiv  Detail & Related papers  (2025-09-16T19:41:48Z)
• Serving Large Language Models on Huawei CloudMatrix384 [28.88558053380112]
  Traditional AI clusters face limitations in compute intensity, memory bandwidth, inter-chip communication, and latency.<n>This paper introduces Huawei CloudMatrix, a next-generation AI architecture realized in the production-grade CloudMatrix384 supernode.<n>It integrates 384 Ascend 910 NPUs and 192 Kunpeng CPUs interconnected via an ultra-high-bandwidth Unified Bus (UB) network, enabling direct all-to-all communication and dynamic pooling of resources.
  arXiv  Detail & Related papers  (2025-06-15T03:41:34Z)
• MiniCPM4: Ultra-Efficient LLMs on End Devices [126.22958722174583]
  MiniCPM4 is a highly efficient large language model (LLM) designed explicitly for end-side devices.<n>We achieve this efficiency through systematic innovation in four key dimensions: model architecture, training data, training algorithms, and inference systems.
  arXiv  Detail & Related papers  (2025-06-09T16:16:50Z)
• Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs [111.69640966866059]
  Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models.<n>In this paper, we aim to uncover a recipe to harness such scale on Ascend NPUs.<n>The key goals are better usage of the computing resources under the dynamic sparse model structures and materializing the expected performance gain on the actual hardware.
  arXiv  Detail & Related papers  (2025-05-07T15:46:36Z)
• Puzzle: Distillation-Based NAS for Inference-Optimized LLMs [17.72841008597783]
  Large language models (LLMs) offer remarkable capabilities, yet their high inference costs restrict wider adoption.<n>We present Puzzle, a hardware-aware framework that accelerates the inference of LLMs while preserving their capabilities.<n>We showcase our framework's impact via Llama-3.1-Nemotron-51B-Instruct (Nemotron-51B) and Llama-3.3-Nemotron-49B, two publicly available models.
  arXiv  Detail & Related papers  (2024-11-28T13:45:42Z)
• DiPaCo: Distributed Path Composition [31.686642863608558]
  We propose a co-designed modular architecture and training approach for machine learning models. During training, DiPaCo distributes by paths through a set of shared modules. At inference time, only a single path needs to be executed for each input, without the need for model compression.
  arXiv  Detail & Related papers  (2024-03-15T18:26:51Z)
• MobileNMT: Enabling Translation in 15MB and 30ms [53.75988363281843]
  We present MobileNMT, a system that can translate in 15MB and 30ms on devices. With the co-design of model and engine, compared with the existing system, we speed up 47.0x and save 99.5% of memory with only 11.6% loss of BLEU.
  arXiv  Detail & Related papers  (2023-06-07T08:25:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.