Julien Simon

@UCVonoXm3SI_Q0ZNHd5JPawA - 557K subscribers

Welcome! This channel is hosted by Julien Simon, now AI Operating Partner at Fortino (www.fortino.group), former Chief Evangelist at Arcee.ai, Chief Evangelist at Hugging Face, and Global Evangelist for AI and Machine Learning at Amazon Web Services. Please subscribe for quality technical content on building AI/ML solutions with Small Language Models, AWS, and more. Personal website: www.julien.org Substack: www.airealist.ai Business inquiries: [email protected]

Home Videos Live Playlists

Qwen 3.5 MoE + TurboQuant + mem0: A Local RAG Chatbot That Remembers

Qwen 3.5 MoE + TurboQuant + mem0: A Local RAG Chatbot That Remembers Julien Simon

35K views - 3 weeks ago

Benchmarking TurboQuant with MLX on Apple Silicon

Benchmarking TurboQuant with MLX on Apple Silicon Julien Simon

34K views - 1 month ago

Web app + Mobile + Stripe + Pitch Deck: one Replit project!

Web app + Mobile + Stripe + Pitch Deck: one Replit project! Julien Simon

22K views - 1 month ago

From issue to PR in 15 minutes with Cursor & Composer

From issue to PR in 15 minutes with Cursor & Composer Julien Simon

21K views - 1 month ago

Stop Coding Alone! Build an 'Opus + M2.7' AI Expert Team

Stop Coding Alone! Build an 'Opus + M2.7' AI Expert Team Julien Simon

49K views - 1 month ago

Deep Dive: How Three MoE Reasoning Models Actually Work — Trinity, DeepSeek R1, Kimi K2 - Part 2

Deep Dive: How Three MoE Reasoning Models Actually Work — Trinity, DeepSeek R1, Kimi K2 - Part 2 Julien Simon

30K views - 2 months ago

Deep Dive: How Three MoE Reasoning Models Actually Work — Trinity, DeepSeek R1, Kimi K2

Deep Dive: How Three MoE Reasoning Models Actually Work — Trinity, DeepSeek R1, Kimi K2 Julien Simon

26K views - 2 months ago

Deep Dive: LLM Quantization, part 3 - FP8, FP4

Deep Dive: LLM Quantization, part 3 - FP8, FP4 Julien Simon

29K views - 3 months ago

No Cloud, No API Keys: Local Open-Source Coding with Trinity Mini, OpenCode, and MLX

No Cloud, No API Keys: Local Open-Source Coding with Trinity Mini, OpenCode, and MLX Julien Simon

19K views - 3 months ago

Deep Dive: Teaching Arcee Trinity Mini to Read Medical Research with RLVR and GRPO

Deep Dive: Teaching Arcee Trinity Mini to Read Medical Research with RLVR and GRPO Julien Simon

25K views - 4 months ago

Open-source Coding with Cline and Arcee Trinity Large

Open-source Coding with Cline and Arcee Trinity Large Julien Simon

24K views - 4 months ago

Building a Kanban Task Management Web App from Scratch with Replit

Building a Kanban Task Management Web App from Scratch with Replit Julien Simon

33K views - 5 months ago

Claude Opus 4.6 and Agent Teams

Claude Opus 4.6 and Agent Teams Julien Simon

25K views - 5 months ago

Trinity Large: An Open 400B MoE Model

Trinity Large: An Open 400B MoE Model Julien Simon

23K views - 5 months ago

Build Mobile Apps with Replit in Minutes!

Build Mobile Apps with Replit in Minutes! Julien Simon

25K views - 5 months ago

Verdent : AI Coding with Parallel Agents — Full Demo!

Verdent : AI Coding with Parallel Agents — Full Demo! Julien Simon

20K views - 5 months ago

Advanced RAG Techniques with Arcee Trinity Mini (100% Local)

Advanced RAG Techniques with Arcee Trinity Mini (100% Local) Julien Simon

19K views - 5 months ago

Build a Reasoning AI Chatbot with Arcee AI Trinity Mini + Gradio + OpenRouter

Build a Reasoning AI Chatbot with Arcee AI Trinity Mini + Gradio + OpenRouter Julien Simon

17K views - 6 months ago

Build web apps in minutes with Replit Design Mode!

Build web apps in minutes with Replit Design Mode! Julien Simon

20K views - 7 months ago

Introducing the Arcee AI Trinity Models

Introducing the Arcee AI Trinity Models Julien Simon

20K views - 7 months ago

The Truth About MCP: Pros, Cons & Real-World Use Cases

The Truth About MCP: Pros, Cons & Real-World Use Cases Julien Simon

26K views - 9 months ago

Running AFM-4.5B on Intel CPUs with OpenVINO

Running AFM-4.5B on Intel CPUs with OpenVINO Julien Simon

32K views - 9 months ago

SLM Inference on a Windows laptop 🤯 Intel Lunar Lake CPU/GPU/NPU + OpenVINO

SLM Inference on a Windows laptop 🤯 Intel Lunar Lake CPU/GPU/NPU + OpenVINO Julien Simon

25K views - 11 months ago

Building an AI Meeting Companion with AFM-4.5B and llama.cpp.

Building an AI Meeting Companion with AFM-4.5B and llama.cpp. Julien Simon

26K views - 11 months ago

Deep Dive: Model Merging with Arcee Fusion

Deep Dive: Model Merging with Arcee Fusion Julien Simon

25K views - 1 year ago

Judging AFM-4.5B with DeepSeek-R1 670B

Judging AFM-4.5B with DeepSeek-R1 670B Julien Simon

49K views - 1 year ago

3 production-ready models released by Arcee AI on Hugging Face

3 production-ready models released by Arcee AI on Hugging Face Julien Simon

21K views - 1 year ago

Homunculus 12B and GLM-4-32B-Base-32K: 2 new Arcee AI research-oriented models

Homunculus 12B and GLM-4-32B-Base-32K: 2 new Arcee AI research-oriented models Julien Simon

22K views - 1 year ago

Retail AI at the edge - Cisco Live 2025 interview

Retail AI at the edge - Cisco Live 2025 interview Julien Simon

22K views - 1 year ago

Arcee AI webinar: routing your function calling and reasoning queries with Arcee Conductor

Arcee AI webinar: routing your function calling and reasoning queries with Arcee Conductor Julien Simon

25K views - 1 year ago

Routing reasoning queries to the best SLM/LLM with Arcee Conductor

Routing reasoning queries to the best SLM/LLM with Arcee Conductor Julien Simon

24K views - 1 year ago

Routing function calling queries to the best SLM/LLM with Arcee Conductor

Routing function calling queries to the best SLM/LLM with Arcee Conductor Julien Simon

24K views - 1 year ago

Comparing SLMs and LLMs with similarity metrics

Comparing SLMs and LLMs with similarity metrics Julien Simon

21K views - 1 year ago

Building a RAG chatbot with LangChain, Chroma, Hugging Face, and Arcee Conductor

Building a RAG chatbot with LangChain, Chroma, Hugging Face, and Arcee Conductor Julien Simon

53K views - 1 year ago

Arcee AI webinar: build agentic workflows with Arcee Orchestra

Arcee AI webinar: build agentic workflows with Arcee Orchestra Julien Simon

34K views - 1 year ago

Arcee AI webinar: pick the right SLM/LLM for each query with Arcee Conductor

Arcee AI webinar: pick the right SLM/LLM for each query with Arcee Conductor Julien Simon

30K views - 1 year ago

Model routing with Open WebUI and Arcee Conductor

Model routing with Open WebUI and Arcee Conductor Julien Simon

38K views - 1 year ago

Arcee Conductor: advanced model routing selects the best SLM/LLM automatically!

Arcee Conductor: advanced model routing selects the best SLM/LLM automatically! Julien Simon

39K views - 1 year ago

Arcee Spotlight: a super-fast 7-billion parameter Visual Language Model

Arcee Spotlight: a super-fast 7-billion parameter Visual Language Model Julien Simon

19K views - 1 year ago

Arcee AI in 2 minutes (March 2025)

Arcee AI in 2 minutes (March 2025) Julien Simon

19K views - 1 year ago

Arcee Blitz 24B - A better Mistral Small 3 model

Arcee Blitz 24B - A better Mistral Small 3 model Julien Simon

19K views - 1 year ago

Arcee Maestro 7B - A small language model that outperforms o1-preview

Arcee Maestro 7B - A small language model that outperforms o1-preview Julien Simon

22K views - 1 year ago

Arcee Orchestra - Build an Agentic Workflow to Augment and Localize YouTube Content

Arcee Orchestra - Build an Agentic Workflow to Augment and Localize YouTube Content Julien Simon

27K views - 1 year ago

Arcee Orchestra - Build an Agentic Retrieval Workflow for the Energy Industry

Arcee Orchestra - Build an Agentic Retrieval Workflow for the Energy Industry Julien Simon

16K views - 1 year ago

Arcee Orchestra - Build an Agentic Code Review Workflow

Arcee Orchestra - Build an Agentic Code Review Workflow Julien Simon

27K views - 1 year ago

Run SLMs locally: Llama.cpp vs. MLX with 10B and 32B Arcee models

Run SLMs locally: Llama.cpp vs. MLX with 10B and 32B Arcee models Julien Simon

33K views - 1 year ago

Virtuoso Lite and Virtuoso Medium v2: distilling DeepSeek-V3 to 10B & 32B

Virtuoso Lite and Virtuoso Medium v2: distilling DeepSeek-V3 to 10B & 32B Julien Simon

23K views - 1 year ago

Decoder-only inference: a step-by-step deep dive

Decoder-only inference: a step-by-step deep dive Julien Simon

32K views - 1 year ago

Deep Dive: Model Distillation with DistillKit

Deep Dive: Model Distillation with DistillKit Julien Simon

38K views - 1 year ago

Function calling with Arcee Caller and the OpenAI API

Function calling with Arcee Caller and the OpenAI API Julien Simon

30K views - 1 year ago

Introducing the Arcee Model Engine

Introducing the Arcee Model Engine Julien Simon

30K views - 1 year ago

Deploying Arcee models on Amazon Bedrock

Deploying Arcee models on Amazon Bedrock Julien Simon

49K views - 1 year ago

Deep Dive: Parameter-Efficient Model Adaptation with LoRA and Spectrum

Deep Dive: Parameter-Efficient Model Adaptation with LoRA and Spectrum Julien Simon

25K views - 1 year ago

Deploying Arcee AI models in minutes with Amazon SageMaker JumpStart

Deploying Arcee AI models in minutes with Amazon SageMaker JumpStart Julien Simon

22K views - 1 year ago

Run performant and cost-effective GenAI Applications with AWS Graviton and Arcee AI

Run performant and cost-effective GenAI Applications with AWS Graviton and Arcee AI Julien Simon

25K views - 1 year ago

SLM in Action: SuperNova-Medius, a high-performance 14B model

SLM in Action: SuperNova-Medius, a high-performance 14B model Julien Simon

27K views - 1 year ago

100,000 Julien Simon

650 views - 1 year ago

Arcee.ai and Small Language Models - Mobile World Congress, Las Vegas (10/2024)

Arcee.ai and Small Language Models - Mobile World Congress, Las Vegas (10/2024) Julien Simon

29K views - 1 year ago

Arcee.ai - Tailoring Small Language Models for Enterprise Use Cases (09/2024)

Arcee.ai - Tailoring Small Language Models for Enterprise Use Cases (09/2024) Julien Simon

35K views - 1 year ago

Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour!

Deploying SuperNova-Lite on Inferentia2: the best 8B model for $1 an hour! Julien Simon

26K views - 1 year ago