MLX

Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning — Merve Noyan, Hugging Face

May 13, 2026 · 19:11

Merve Noyan from Hugging Face argues that open-weight and open-source models have caught up with closed models, citing GLM 5.1 topping the Artificial Analysis Intelligence index. She walks through Hugging Face’s ecosystem for agentic AI: benchmark datasets on the Hub to filter models by SWE-bench or AIME scores; inference providers that route to the cheapest or fastest option per model; a traces repository type for storing and exploring agent sessions; and skills that plug into coding agents (e.g., Claude Code) to fine-tune vision-language models on a dataset by name—calculating VRAM, selecting an instance, and launching the job. She demos an agent-driven fine-tuning of Qwen2-VL on a vision-language dataset, and a case study where an LLM agent orchestrated OCR of 30,000 AI papers using open OCR models and Hugging Face Jobs, eliminating napkin math. The MCP server also enables querying Hub models, datasets, and spaces from agents.

Why MLX — Prince Canuma, Neywa Labs

May 11, 2026 · 23:10

Prince Canuma argues that on-device AI, powered by Apple's MLX framework, is a viable alternative to cloud-dependent services, especially for users in regions with unreliable internet. MLX, an array framework for Apple Silicon, has reached 1.5 million downloads and 4000 ported models, including day-zero support for Gemma 4 and Qwen 3 Omni. Canuma demonstrates real-time vision models (e.g., RF Deter for object detection), sub-100ms text-to-speech via Marvis TTS, and modular speech-to-speech pipelines that run entirely on-device. Community projects showcased include a native voice app (Locally), a robot with real-time voice cloning, and a video generation system that chains coherent stories on 16GB VRAM. A recent breakthrough, Turbo Quant, reduces KV cache by 4x, enabling 1 million context windows on-device. Canuma emphasizes that these capabilities provide accessibility for his blind father and enable agents that hear, see, and respond without phoning home.

Running LLMs on your iPhone: 40 tok/s Gemma 4 with MLX — Adrien Grondin, Locally AI

Apr 20, 2026 · 10:51

Adrien Grondin, developer of Locally AI, demonstrates how to run Gemma 4 and other LLMs on iPhone using Apple's MLX framework, achieving 40 tokens per second on the latest devices. He explains that MLX is optimized for Apple Silicon and that the open-source mlx-swift-lm GitHub repo enables easy integration into iOS, macOS, and iPadOS apps in under 10 minutes. Grondin recommends quantized models from the Hugging Face MLX community—typically 4-bit to 8-bit—and shows a live demo of Gemma 4 generating text offline. He confirms that mlx-swift-lm supports tool calling, though structured generation is not yet available. He also notes that Locally AI has been acquired by LM Studio, which now lets users run models via MLX or llama.cpp and connect them through OpenAI or Anthropic-compatible APIs.

Gemma, DeepMind's Family of Open Models — Omar Sanseviero, Google DeepMind

Apr 20, 2026 · 15:26

Omar Sanseviero presents Gemma 4, Google DeepMind's latest family of open models, which range from 2B to 32B parameters and introduce a novel per-layer embedding (E2B) architecture optimized for on-device inference. The models feature multimodal understanding (images, video, audio), multilingual support across 140+ languages, and are released under an Apache 2 license. Within a week, Gemma 4 reached 10 million downloads, contributing to over 500 million total downloads for the Gemma family and 100,000 community-derived models. Sanseviero highlights official variants like Shield Gemma for content safety and MedGemma for medical tasks, as well as community efforts such as AI Singapore's Southeast Asian language models and Sarvam's sovereign AI initiative for India. He emphasizes real-world applications including cancer therapy pathway discovery and fully offline agentic tasks on phones and Raspberry Pis, arguing that open models are rapidly enabling high-performance, private, and customizable AI across diverse use cases.

AI Kernel Generation: What's working, what's not, what's next – Natalie Serrino, Gimlet Labs

Dec 17, 2025 · 19:15

Natalie Serrino, cofounder of Gimlet Labs, presents how AI-generated kernels can automatically speed up custom PyTorch code by up to 24% on Apple M4 hardware using the Metal framework, with a 40% speedup from kernel fusion. The agentic system iterates through compilation, execution, correctness, and optimization, but faces challenges like validation of floating-point results and reliable benchmarking. Successes include rewriting average pool 1D as a convolution for 80% improvement, while failures occur on heavily optimized ops like matrix multiply. A real-world audio encoder model saw 70% faster inference on RTX 6000 Blackwell via six custom fused kernels. Serrino emphasizes that AI is best for rapidly searching optimizations and porting code to new hardware, not for surpassing human experts on novel algorithms.