Donato Capitella

@donatocapitella · 113,000 subscribers

View the channel on YouTube

Median views per long-form video

25,716

Uploads per week

0.4

Average long-form length

27:24

In the sample

46 long-form · 4 Shorts

Beat the channel median

GLM 4.5-Air-106B and Qwen3-235B on AMD "Strix Halo" AI Ryzen MAX+ 395 (HP Z2 G1a Mini Workstation)
138.2K views · 5.4x the median
Qwen3.8-Flash-Next on AMD Strix Halo: Halogen, N-grams and Benchmarks
82.3K views · 3.2x the median
Kimi-K2(1T)/GLM 4.7(355B) on a 4-Node Strix Halo Cluster - 512GB of Unified Memory
81.3K views · 3.2x the median
Dual AMD Radeon 9700 AI PRO: Building a 64GB LLM/AI Server with Llama.cpp
78.9K views · 3.1x the median
Refurbished 64GB VRAM AI Server for Local AI: 4x NVIDIA V100/P100, AMD MI25
76.8K views · 3.0x the median

Trailed the channel median

Spikee #4 - Bypassing LLM Guardrails (Anti-spotlighting, Best of N attacks)
6.7K views · 0.3x the median
Channel Update, AMD Advancing AI, Gorgon Halo (192GB), ROCmFPX, LuceBox, Lemonade, Kimi K3, Laguna
6.1K views · 0.2x the median
Running models on 32GB, Muse 30B, Qwen 3.8, New Agentic Benchmarks, Toolbox Updates / Discord
5.7K views · 0.2x the median
LLM Chronicles #6.3a: OpenAI CLIP for Zero-Shot Image Classification and Similarity
2.5K views · 0.1x the median
Spikee #2 - Hands-on Prompt Injection Testing with Custom Dataset
1.7K views · 0.1x the median

Latest uploads

The 50 most recent uploads, newest first. Shorts are included; the badge marks them.

Title	Published	Length	Views
DeepSeek V4.1 Flash 1017 Update: 44% Fewer Tokens, Running on Strix / Gorgon Halo with DwarfStar	Oct 18, 2026	8:34	10.2K
Qwen3.8 27B and Flash Next on Single/Dual AMD Radeon 9700: Engine Benchmarks and Setup	Oct 16, 2026	19:22	29K
Thoughts on 2-Bit Quantization, IQ2_XXS, imatrix and antirez's DeepSeek quant	Oct 5, 2026	14:48	27.9K
DeepSeek V4.1 Flash on Strix Halo (Dwarf Star) #amd_partnerShort	Sep 23, 2026	1:16	4.7K
DeepSeek V4.1 Flash on Strix Halo: Single-Node SSD vs Two-Node Cluster (DwarfStar)	Sep 23, 2026	18:40	47.9K
Fast Qwen 3.8-Flash-Next on Ryzen AI HaloShort	Sep 11, 2026	1:03	15.6K
Qwen3.8-Flash-Next on AMD Strix Halo: Halogen, N-grams and Benchmarks	Sep 11, 2026	18:10	82.3K
August Model Bonanza: Qwen 3.8-Flash-Next and GLM 5.3-FlashShort	Aug 31, 2026	2:59	8.4K
AMD Ryzen AI HaloShort	Aug 26, 2026	0:39	371K
Running models on 32GB, Muse 30B, Qwen 3.8, New Agentic Benchmarks, Toolbox Updates / Discord	Aug 12, 2026	14:19	5.7K
Channel Update, AMD Advancing AI, Gorgon Halo (192GB), ROCmFPX, LuceBox, Lemonade, Kimi K3, Laguna	Jul 30, 2026	26:37	6.1K
How I Configure the Ryzen AI Halo (Strix Halo) for 10-15% Faster Local Inference	Jul 14, 2026	20:54	47.8K
Building and Running a Deep Research Agent locally on Strix Halo & R9700 AI PRO	Jul 7, 2026	39:03	25.7K
Refurbished 64GB VRAM AI Server for Local AI: 4x NVIDIA V100/P100, AMD MI25	Jul 3, 2026	34:49	76.8K
GLM 5.2 on Dual Strix Halo (256GB): Worth it?	Jun 25, 2026	18:29	65.7K
DeepSeek V4 Flash Inference on Strix Halo: ds4, Quantizations, Distributed Inference and Benchmarks	Jun 15, 2026	31:38	50.5K
Intel Arc Pro B70 (32GB) for Local LLMs: llama.cpp (SYCL/Vulkan), vLLM (Intel LLM Scaler) Benchmarks	May 29, 2026	26:37	70.6K
Local Coding Agents on Strix Halo and R9700: Pi, Opencode, and SWE-bench Mini Benchmarks	May 22, 2026	41:51	63.4K
MTP (Multi-Token Prediction): 2x Faster Token Generation on AMD Strix Halo & Radeon 9700 AI Pro	May 18, 2026	17:50	47.2K
AMD MI50 32GB for Local AI: Qwen 3.6 & Gemma 4 on llama.cpp / vLLM (vs R9700)	May 9, 2026	29:25	66.9K
Strix Halo & R9700 AI PRO Updates: Qwen 3.6 and Gemma 4 Support, ROCm 7.2.2 and Two New Series	May 1, 2026	15:01	25.5K
Fast Finetuning of Gemma-3, Qwen-3 and GPT-OSS on Strix Halo using Unsloth and Multi-Node Setups	Mar 9, 2026	31:45	11.1K
ComfyUI Strix Halo Toolbox for Image and Video Generation (LTX2, Qwen Image, WAN 2.2, Hunyuan 1.5)	Feb 18, 2026	18:12	19.7K
Low-Latency Strix Halo Cluster with RDMA (RoCE/Intel E810) and vLLM, Framework Desktop Boards	Feb 8, 2026	16:18	54.4K
Kimi-K2(1T)/GLM 4.7(355B) on a 4-Node Strix Halo Cluster - 512GB of Unified Memory	Jan 23, 2026	9:36	81.3K
ROCm+Linux Support on Strix Halo: It's finally stable in 2026!	Jan 18, 2026	12:20	21.5K
Video and Image Generation on AMD R9700 AI PRO (Qwen Image, Wan 2.2, Hunyuan 1.5)	Jan 4, 2026	41:36	25.4K
Running vLLM on Strix Halo (AMD Ryzen AI MAX) + ROCm Performance Updates	Dec 24, 2025	18:06	50.4K
vLLM on Dual AMD Radeon 9700 AI PRO: Tutorials, Benchmarks (vs RTX 5090/5000/4090/3090/A100)	Dec 15, 2025	23:39	39.2K
Dual AMD Radeon 9700 AI PRO: Building a 64GB LLM/AI Server with Llama.cpp	Dec 8, 2025	50:30	78.9K
Building a Two-Node AMD Strix Halo Cluster for LLMs with llama.cpp RPC (MiniMax-M2 & GLM 4.6)	Nov 9, 2025	26:53	19.4K
Finetuning LLMs on Strix Halo – Full, LoRA, and QLoRA on Gemma-3, Qwen-3, and GPT-OSS-20B	Oct 20, 2025	55:05	18.6K
VibeVoice (Speech Generation/Voice Cloning) on Framework Desktop with Strix Halo (AMD AI Ryzen MAX+)	Sep 21, 2025	13:17	7.2K
Run Qwen Image and WAN 2.2 on Framework Desktop with Strix Halo (AMD AI Ryzen MAX+ 395) - Full Guide	Aug 29, 2025	24:44	26.8K
GLM 4.5-Air-106B and Qwen3-235B on AMD "Strix Halo" AI Ryzen MAX+ 395 (HP Z2 G1a Mini Workstation)	Aug 5, 2025	26:40	138.2K
LLM Chronicles #6.9: Design Patterns for Securing LLM Agents Against Prompt Injection (Paper Review)	Jun 29, 2025	33:56	22.6K
Zero-Click M365 Copilot Exploit 'EchoLeak' - Deep Dive	Jun 14, 2025	38:17	12.2K
Spikee #4 - Bypassing LLM Guardrails (Anti-spotlighting, Best of N attacks)	Jun 1, 2025	47:01	6.7K
Understanding Reasoning LLMs (o1/o3, DeepSeek-R1, Gemini Thinking, Grok 3, Claude 3.7)	Mar 15, 2025	23:20	23K
Spikee #3 - Prompt Injection Testing of a GenAI Feature in an LLM Application	Feb 19, 2025	23:11	12.2K
Spikee #2 - Hands-on Prompt Injection Testing with Custom Dataset	Feb 6, 2025	34:05	1.7K
Spikee #1 - LLM Benchmarking/Testing Tool for Prompt Injection	Feb 3, 2025	29:27	10.3K
Hacking and Securing LLM Applications - Should you let ChatGPT Control Your Browser [DeepSec 2024]	Dec 14, 2024	39:56	13K
Multi-Chain Prompt Injection and Jailbreaking of LLM Applications	Dec 9, 2024	47:10	10.8K
LLM Chronicles #6.7: Faithfulness Checks for RAG pipelines (gpt4o-mini, Llama-index, RAGAS, Azure)	Nov 15, 2024	37:36	13.7K
LLM Chronicles #6.6: Hallucination Detection and Evaluation for RAG systems (RAGAS, Lynx)	Nov 5, 2024	12:43	26.7K
LLM Chronicles #6.3a: OpenAI CLIP for Zero-Shot Image Classification and Similarity	Oct 15, 2024	22:13	2.5K
LLM Chronicles #6.5: Build LLM Agents from Scratch: PAL, ReAct & Langchain in 1 Hour	Sep 15, 2024	1:09:42	35.7K
Microsoft 365 Copilot Hack Breakdown [Black Hat 2024]	Aug 23, 2024	21:24	27.3K
LLM Chronicles #6.4: LLM Agents with ReAct (Reason + Act)	Jul 19, 2024	15:46	52.7K

See what separates this channel's best and worst videos

The free channel scan reads this channel's public videos and transcripts and reports the patterns behind its winners and losers, with verbatim quotes. Free, no signup.

Run the free channel scan

Writing a video like these? Check the script before you record.

Where these numbers come from

Counts from the YouTube Data API, read Oct 19, 2026. Refreshed at least every 7 days. The sample covers uploads published Jul 19, 2024 to Oct 18, 2026. A channel that would rather this page did not exist can ask for its removal through the contact page, and it is removed.

YouTube channel stats

Reading the channel

Pulling the latest uploads from YouTube. This usually takes a few seconds.