与「Gemma」相关的搜索结果

Meet the Gemma Translator! A fully offline device powered by Gemma 4 E2B built with @Antigravity. Running entirely on a Raspberry Pi 5 with a connected microphone and speaker, this highly portable prototype is housed inside a custom, 3D-printed case.

让 8 美元的 ESP32-S3 芯片跑起近 2900 万参数的 LLM。诀窍是把大部分参数放在 Flash 里而不是 RAM 里，靠的是 Google Gemma 的 Per-Layer Embeddings 思路。

Nanbeige4.2-3B：开源高性能超小模型 3B大小，评分超过Gemma4 4B、Qwen3.5 4B，由Boss直聘的LLM团队“南北阁”开源。（怎么是个公司都做模型了？） 模型：

Earlier this week, we shared some recent AI highlights across Google. Here are some milestones showing our progress from the past few months ↓ 🚀 The Gemini app now has 950 million monthly active users, with daily active users tripling in the last year. 🔨 More than 9 million developers are building each month with our models across our APIs and key developer products. 📽️ Since launching Omni at I/O in May, there’s been a 40% increase in daily active users creating videos in the @GeminiApp. 📈 Our latest Gemma 4 models have been downloaded over 300 million times since launching in April. 👥 Our agentic development platform @GoogleAntigravity has more than 2.4 million weekly active users. 🔎 Since expanding AI Mode in Search globally last October, we’ve surpassed 1 billion monthly active users. 🖥️ Nearly 90% of Fortune 100 companies are using Gemini Enterprise.

LiveKit 针对 Gemma 4 31B 进行优化 在实时语音方面比 GPT-4.1 快 5 倍、成本六分之一 LiveKit 上线一项新服务：在自家推理平台 LiveKit Inference 上跑 Google 新一代大模型 Gemma 4 31B 跟 GPT-4.1 比：接话延迟低 5.2 倍（首字 192 毫秒对 1006 毫秒）、成本便宜约 83%（大概六分之一） 酒店前台场景测试任务完成率 88%，超过 GPT-4.1（73%）和 Gemini 2.5 Flash（64%）...

Google 在 Pixel 10 上跑 Gemma 4 三万英尺的客舱断网也能聊天、看图、改设置 在Google I/O India 上，Tensor 团队和 Pixel 团队联合演示：把 Gemma 4 轻量版直接塞进手机里的 TPU里 不仅能能聊天」，还能「看图、听写、控制手机」 官方演示：手机在断网状态下做旅行规划、菜谱推荐和家居自动化

QVAC SDK 0.15.0 is live. This release adds multiple prompts batching, brings a native AMD GPU backend to the stack, moves more vision encoders onto mobile GPUs, and adds a second local coding-agent integration. Main highlights: - Prompt batching for the LLM addon. Batch multiple prompts into one job and process them concurrently, with each answer returned the moment its generation finishes. - Native AMD GPU backend. A first-class HIP/ROCm backend in @qvac/vla-ggml, auto-selected over Vulkan with clean fallback when ROCm is absent. - A second local coding agent. OpenClaw joins OpenCode for local, cloud-free agent workflows. AGENTS - OpenCode plugin update (@qvac/opencode-plugin). Aligned with the current SDK, CLI, and AI SDK provider packages. A fresh install runs @OpenCode against managed local QVAC models out of the box, from the default qvac/qwen3.5-9b, with no manual qvac serve setup. - OpenClaw plugin (@qvac/openclaw-plugin). A second coding-agent integration alongside OpenCode. A fresh setup installs the plugin, creates a local qvac provider through onboarding, and runs a QVAC model through @OpenClaw's local service path. LANGUAGE MODELS - Prompt batching (LLM addon). Batch multiple prompts in one job and run them concurrently, each answer returns the moment its generation finishes, no waiting on the others. - Reasoning-context trimming on hybrid + recurrent models (@qvac/llm-llamacpp). remove_thinking_from_context now works beyond pure-attention models. Same JS API, no throw. VOICE AND SPEECH - Transcription (transcription-parakeet 0.9.0). More robust CPU fallback on GPU failure and a faster Vulkan backend on Pixel 9. - Text-to-speech features (tts-ggml 0.4.0). Adds LavaSR for noise removal and adjustable output frequency up to 48 kHz, plus Japanese via Chatterbox. - Text-to-speech fixes (tts-ggml 0.4.1). CPU fallback on GPU failure, a q8_0 KV crash fix on Metal with Chatterbox. VISION - Qwen3.5 vision encoder on GPU (Android). Image encoder moves onto the phone GPU, with a smarter tile-grid preprocessor and default image-token caps, for flagship Android: Vulkan on Mali (Pixel 9 Pro) and OpenCL on Adreno 830 (Galaxy S25). - Gemma-4 vision encoder on GPU (Android). Vision encoder runs on the phone GPU instead of CPU, same flagship Android targets. PLATFORM AND PERFORMANCE - AMD GPU backend (@qvac/vla-ggml). Native HIP/ROCm backend, auto-selected over Vulkan with clean fallback when ROCm is absent (Linux x64 only). Comes with ~23% faster than Vulkan, ~14% faster than PyTorch-ROCm, parity preserved. Unified code style. A cleaner, more consistent, easier-to-contribute codebase. Let's build. npm install @qvac/sdk