Videos
| Thumb | Title | Channel | Status | Published |
|---|---|---|---|---|
|
Running Qwen 3.8 Flash Next on a $1000 Local AI Build with Strata
Qwen 3.8 Flash Next, served by the Strata engine on a roughly $1,000 secondhand build, generated a fully interactive... |
Digital Spaceport | summarized | 2026-10-10 02:11 |
|
19 Months of ChatGPT Pro....or a Mac Studio?
OpenAI's September 29th halving of ChatGPT Pro allowances means 19 months of the $200 plan now costs the same as a... |
Cloud Codes | summarized | 2026-10-04 19:00 |
|
Before You Run AI Locally, Watch This
Model listings show only weight file size, not the full memory bill: KV cache grows with context and can match the... |
Cloud Codes | summarized | 2026-09-30 12:34 |
|
How to Build Things with Jev & OpenJevs
Jev, from Typesafe AI, is a system-one model that returns typed answers with probabilities instead of generating... |
Sam Witteveen | summarized | 2026-09-21 14:30 |
|
The Local Coding Breakthrough We Waited For? (Bonsai 2)
Bonsai 2 compresses Qwen 3.8 from 54GB to 5.9GB using ternary quantization (1.76 bits per weight), claiming 98%... |
Cloud Codes | summarized | 2026-09-19 04:30 |
|
What It Costs to Run DeepSeek V4.1 Flash Locally?
Running DeepSeek V4.1 Flash locally requires at least 510 GB of storage and a multi-GPU setup costing tens of... |
Cloud Codes | summarized | 2026-09-11 19:30 |
|
GLM 5.3 Flash Local Ai Test
GLM 5.3 Flash, tested locally at 1-bit quantization, demonstrated strong reasoning capabilities by generating a... |
Digital Spaceport | summarized | 2026-08-28 10:00 |
|
26 Billion Parameters. 2 GB of RAM
Turbo Field Fair runs a 26B parameter Mixture of Experts model on a Mac with only 2GB of RAM by keeping the shared... |
Cloud Codes | summarized | 2026-08-25 12:00 |
|
Ornith 1.5 35B is INSANE - Full Test & Quant Comparison!
Ornith 1.5 35B-A3B, a Mixture of Experts model based on Qwen 3.5, shows impressive capability for its size,... |
Bijan Bowen | summarized | 2026-08-22 11:06 |
Frontier News · by Hyperjump Technology