Upload date
All time
Last hour
Today
This week
This month
This year
Type
All
Video
Channel
Playlist
Movie
Duration
Short (< 4 minutes)
Medium (4-20 minutes)
Long (> 20 minutes)
Sort by
Relevance
Rating
View count
Features
HD
Subtitles/CC
Creative Commons
3D
Live
4K
360°
VR180
HDR
427 results
513 subscribers
The same Radeon GPU, the same Qwen model, no new quantization trick: 9.7 tokens per second became 37.2. llama.cpp already ...
14,736 views
3d ago
Four M5 Ultra Mac Studios, wired together with Thunderbolt 5 cables, ran Meta's 816-billion-parameter Muse Spark Open locally ...
590 views
5d ago
A jailbroken PlayStation 5 is now running Qwen 3.8 27B locally on its own GPU, at around 20 tokens per second. Not through the ...
2,112 views
7d ago
Microsoft just ran a 137-billion-parameter coding model locally on a Windows laptop. Not through an API, not on a remote server, ...
375 views
10d ago
llama.cpp just made the exact same model run more than twice as fast on the exact same GPU. It is not a new quantization format, ...
11,102 views
2w ago
A 125-billion-parameter AI model, generating almost 100 tokens per second. On an RTX 5070 with 12 GB of VRAM. Not a server ...
1,396 views
850 tokens per second. From a 35-billion-parameter model. On one RTX 5090, with the full 262K-token context window. That is ...
111 views
A 502 GB model file. One RTX 5090 with 32 GB of VRAM. About 128 GB of system memory. Even combined, the model doesn't fit ...
959 views
3w ago
A 27-billion-parameter Qwen model ran with a one-million-token agent workspace on a laptop with a 24 GB GPU — and still ...
4,345 views
An 82-gigabyte model file. A graphics card with 12 gigabytes of VRAM. And the model is generating tokens — not one every few ...
14,035 views
4w ago
5 subscribers
1 subscribers
7 subscribers
Solving LeetCode 1331: Rank Transform of an Array using C++. In this video, we break down the LeetCode daily coding ...
61 views
3mo ago
Remove Covered Intervals (LeetCode 1288) explained from first principles — starting with the brute-force O(n²) approach, then ...
4 views
TypeSafe publishes the benchmark for its own model. On it, Jev scores 67.8% accuracy. So does Claude Sonnet 5. Exactly 67.8% ...
129 views
1mo ago
In July, a group of AI agents was supposed to be sealed off from the internet. They weren't. Stuck on a security challenge, they ...
322 views
DeepSeek just took one of the most expensive parts of long-context AI inference and made it 437 times smaller. Not the model.
1,745 views
A coding agent can send 115000 tokens to a model and have almost nothing new to say. In a dataset of 739 anonymized Claude ...
24,897 views
A car dealer put a ChatGPT-powered chatbot on its website. Someone typed one instruction, and it agreed to sell a brand new ...
8 views
8d ago
Claude Fable 5.1 did not get cheaper in the normal way. Its base API price is still $10 per million input tokens and $50 per million ...
267 views
A lawyer asked ChatGPT for court cases. It gave him six. None of them existed, and when he asked if they were real, it said yes.
158 views
9d ago
way. Topics Covered: ✓ What is OOP? ✓ Why do we use OOP? ✓ OOP as a Programming Approach ✓ Real-Life Recipe Book ...
40 views
4mo ago
Why can the same Qwen 3.8 27B model run at 60 tokens per second on one setup and well above 100 on another—using the ...
883 views
