Radar Telegram alerts Open Radar

No graphics card? This free AI with disclaimer removed runs on a 2019 laptop A key runs it on a 2019 laptop with 8 GB of RAM and only built graphics. Screenshot: 11.4 indicates a second, all on the processor, & #036;0 per month. The terms: 1. Install Ollama without an available graphics card, it runs on the processor itself. 2. Get a Decensored Building of Google Gemma 4 E4B, file 4.8 GB: ollama run hf.co/igorls/gemma-4-E4B-it-q4 0-unquantized-her-GGUF:Q4 0 0 type / start nothink on CPU, thinking costs minutes. Keep the context short to save memory: / start parameter number 8192 5. Run ollama ps to see if it is using CPU, GPU or both. In the most difficult test, he refuses 21% of the time with thinking, compared to about 98%, on the model page. Our verdict: fine for writing, chat and drafts, bad for hard thinking and coding agents. The terms:

תרגם לעברית

aipost · · Source

No graphics card? This free AI with disclaimer removed runs on a 2019 laptop A key runs it on a 2019 laptop with 8 GB of RAM and only built graphics. Screenshot: 11.4 indicates a second, all on the processor, & #036;0 per month. The terms: 1. Install Ollama without an available graphics card, it runs on the processor itself. 2. Get a Decensored Building of Google Gemma 4 E4B, file 4.8 GB: ollama run hf.co/igorls/gemma-4-E4B-it-q4 0-unquantized-her-GGUF:Q4 0 0 type / start nothink on CPU, thinking costs minutes. Keep the context short to save memory: / start parameter number 8192 5. Run ollama ps to see if it is using CPU, GPU or both. In the most difficult test, he refuses 21% of the time with thinking, compared to about 98%, on the model page. Our verdict: fine for writing, chat and drafts, bad for hard thinking and coding agents. The terms:

No graphics card? This free AI with disclaimer removed runs on a 2019 laptop A key runs it on a 2019 laptop with 8 GB of RAM and only built graphics. Screenshot: 11.4 indicates a second, all on the processor, & #036;0 per month. The terms: 1. Install Ollama without an available graphics card, it runs on the processor itself. 2. Get a Decensored Building of Google Gemma 4 E4B, file 4.8 GB: ollama run hf.co/igorls/gemma-4-E4B-it-q4 0-unquantized-her-GGUF:Q4 0 0 type / start nothink on CPU, thinking costs minutes. Keep the context short to save memory: / start parameter number 8192 5. Run ollama ps to see if it is using CPU, GPU or both. In the most difficult test, he refuses 21% of the time with thinking, compared to about 98%, on the model page. Our verdict: fine for writing, chat and drafts, bad for hard thinking and coding agents. The terms:

More on Radar

Want to see every report in real time?

Hundreds of sources worldwide, translated into your language, with alerts for what matters to you.

Sign up free
Share on WhatsApp Get alerts on Telegram