AI Coding Live News

On 2026-11-04 Alibaba Taobao's MNN inference-engine team released MNN-Pocket-0.3B on GitHub (alibaba/MNN) and Hugging Face (taobao-mnn): a roughly 300M-parameter Chinese-English instruction model co-designed with the MNN stack for smartphone apps, under Apache 2.0. The official model card says the INT4 (W4A16) QAT build is only 173 MB, supports 32K context, decodes at up to 466 tok/s on iPad Pro M5 (Metal) and about 350 tok/s in tests on iPhone 18 Pro, and averages 50.00 across 11 zh/en benchmarks, ahead of larger ~500M baselines such as Qwen3-0.6B at 44.28 (all vendor figures). The family also ships Base, SFT, GGUF, an on-device MNN package and a Dec decision model that answers in one forward pass. Since 11-08 the third-party iOS app Local LLM has added it and the community has published a LiteRT conversion. The team explicitly does not recommend it for advanced math or long code generation.

Zoom

On 2026-11-06, India-based 169Pi released Alpie Seed 9B (Apache 2.0): SFT with DoRA plus multi-objective GRPO post-training on Qwen3.5-9B, keeping text/image/video input and a 262K native context, with FP16 plus Q4/Q3/Q2 GGUF builds. Vendor-reported FP16 scores with thinking on: MMLU-Pro 82.54%, GPQA Diamond 84.32%, LiveCodeBench v6 72.99%, SWE-Bench Verified 61.20% (Mini-SWE-agent, no retries), OCRBench 90.30%. The team also reports offline inference on iPhone 17 Pro, Galaxy Z Flip8, Mac M2, and Windows CPU-only.

Zoom

On 2026-11-05 Microsoft Foundry blogged that Foundry Local CLI 0.13.0+ can run 4-bit Qwen3.8-27B (~18 GB weights) on-device via ONNX Runtime and connect it to GitHub Copilot through Bring Your Own Key. Needs an NVIDIA GPU with at least 24 GB VRAM (about 64K context on 24 GB; up to the model's 262K max on 32 GB+). Vendor-cited model-card scores include Terminal-Bench 2.1 73.0 and SWE-bench Pro 61.7; Microsoft also reports higher generation speed than same-quant llama.cpp on RTX 5090 and DGX Spark. Mac and AMD support are still on the roadmap.

Zoom

Anomaly, the company behind open-source coding agent OpenCode, shipped Hex 3.0 stable: hold a shortcut, speak, and the text is pasted at your cursor. Recognition runs on-device, local model memory drops from about 900 MB to about 160 MB, and it adds vocabulary hints, a hex CLI and optional OpenCode rewriting.

Zoom

Microsoft shipped Visual Studio Code 1.143. The Copilot harness, built on the Copilot SDK, is now the default for new sessions and works across the editor and Agents window. A Compare Models preview runs several models on one task with an optional Judge model, an experimental mode runs MAI Code 1.1 Flash on a local NVIDIA GPU, and large chats open much faster.

Zoom

On Oct 20, French voice AI company Gradium open-sourced Phonon, a family of on-device text-to-speech models: the English Phonon 31m (64 MB q8 weights, Apache 2.0) and Phonon 40m (single-language English, French, German, Spanish and Portuguese variants plus a five-language model, CC BY-NC non-commercial). Built on Kyutai's Pocket TTS and the Mimi codec, it ships its own runtime for CPU, Metal, CUDA, Vulkan, WebGPU, Core ML and Snapdragon, running offline on phones, browsers and a Raspberry Pi. Gradium reports 7 ms to first audio on a MacBook Air M5 CPU versus 517 ms for Kokoro.

Zoom

Perplexity officially unveiled that Perplexity Computer now operates 100% locally on macOS through the native desktop application. Breaking away from cloud-dependent computer-use paradigms that ship continuous video feeds across the internet, Perplexity Computer executes both the underlying inference model and the agent orchestration runtime directly on local Mac silicon. By interfacing natively with macOS Accessibility APIs, the system eliminates network latency, guarantees complete screen privacy, and empowers autonomous desktop copilots to orchestrate multi-application workflows entirely offline.

Zoom

Meta AI published the technical report for Muse Glimmer 30B (arXiv:2610.24628), an open-source 30-billion parameter causal language model with an integrated perception encoder designed for on-device autonomous agents. Quantized to approximately 4 bits, Muse Glimmer operates inside 32GB of VRAM on a single consumer GPU (such as an RTX 5090) without cloud reliance. On rigorous agentic evaluations, Muse Glimmer sets new records for its size class: achieving 75.5 on MCPAtlas (surpassing Gemma4-31B at 54.2 and Qwen3.6-27B at 62.5) and 51.2 on SWE-Bench Pro, released fully under the Apache 2.0 license.

Zoom

On Oct 13 Liquid AI released LFM2.5-24B-A2B, the largest and final LFM2.5 model: 24B total parameters, ~2.45B active per token, 131K context, and always-on reasoning. By Liquid's own numbers it leads or matches Qwen3.6-35B-A3B on 5 of 8 tool-use/agent benchmarks (AutomationBench 27.69 vs 8.72) while trailing on SWE-Bench Verified, GPQA and other knowledge/coding tests. Open weights are on Hugging Face with GGUF, MLX, FP8 and ONNX builds; API pricing is $0.10 / $1.00 per million tokens and it is also on OpenRouter.

Zoom

On 2026-10-12 OpenBMB released MiniCPM-V 4.7, an Apache-2.0 open multimodal family with a 35B-A3B variant (the series' first MoE) and a 1B variant. Its Lookahead Expert Scheduling (LES) prefetches experts across layers and, combined with layer-wise mixed-precision quantization and DSpark speculative sampling, lifts SSD-offloaded decoding on an iPad Pro M4 (16GB) from 2.97 to 17.39 tokens/s (5.86x), per OpenBMB. Weights are on Hugging Face, ModelScope and Ollama, with vLLM, SGLang, llama.cpp and iOS/Android/HarmonyOS support.

Zoom

At its Oct 7 Windows event Microsoft shipped an on-device MAI-Code-1.1-Flash (137B total / 6.8B active MoE, 256K context, ~3.3 bits per weight) on RTX Spark PCs, scoring 70.80% SWE-Bench Verified and 66.29% Terminal-Bench 2.1 locally. GitHub HydraFusion will route Copilot tasks between local and cloud models in experimental preview later in October, with no inference charge for local calls; MXC agent containment went GA the same day.

Zoom

Alibaba Qwen (@Alibaba_Qwen) launched Qwen Intelligence with three SOTA mobile agents: Mobile Planner (plans/decomposes/orchestrates; #1 on MobilePA-Bench and related boards), Mobile-Use (API-first with GUI fallback; MobileWorld 82.1, MobileWorld-Real 92.2, ~90% end-to-end success), and Mobile Creative (~3s image generation). The team also opened MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety covering planning, cross-app execution, on-device performance, and safety.

Zoom

@DanKornas highlighted MarkuprPlus (github.com/hashfunction/MarkuprPlus), an MIT desktop app, CLI, and MCP that turns window-locked screen recordings plus on-device Whisper narration into structured Markdown (one annotated screenshot per mark) for Claude Code, Cursor, Codex, and Windsurf. Local-first session folders keep reports, screenshots, video, audio, and metadata together.

Zoom

@DanKornas highlighted Interceptor (github.com/Hacker-Valley-Media/Interceptor), an agent browser and macOS control stack: one CLI plus extension drives your existing Chrome/Brave/Safari session (cookies, logins, tabs intact), with page actions, passive network capture, record-and-replay, and macOS accessibility/trusted input plus on-device vision/speech. Wires into Claude Code, Codex, Gemini CLI, and Cursor.

Zoom