▶
Saturday, December 23, 2023
▶
Thursday, December 21, 2023
Tuesday, December 19, 2023
Thursday, December 14, 2023
Sunday, December 10, 2023
Thursday, December 7, 2023
Wednesday, December 6, 2023
Sunday, December 3, 2023
Wednesday, November 29, 2023
Friday, November 24, 2023
Sunday, November 19, 2023
Saturday, November 18, 2023
Wednesday, November 15, 2023
Friday, November 10, 2023
Wednesday, November 8, 2023
Sunday, November 5, 2023
Friday, November 3, 2023
Sunday, October 29, 2023
Wednesday, October 25, 2023
Sunday, October 22, 2023
Thursday, October 19, 2023
Sunday, October 15, 2023
Wednesday, October 11, 2023
Monday, October 9, 2023
Thursday, October 5, 2023
Monday, October 2, 2023
Wednesday, September 27, 2023
Monday, September 25, 2023
Friday, September 22, 2023
Tuesday, September 19, 2023
Sunday, September 10, 2023
Saturday, September 2, 2023
Wednesday, August 30, 2023
Sunday, August 27, 2023
Wednesday, August 23, 2023
Monday, August 21, 2023
Friday, August 18, 2023
Monday, August 14, 2023
Friday, August 11, 2023
Tuesday, August 8, 2023
Saturday, August 5, 2023
Monday, July 31, 2023
Monday, July 24, 2023
Monday, July 17, 2023
Friday, July 14, 2023
Saturday, July 8, 2023
Tuesday, July 4, 2023
Thursday, June 29, 2023
Friday, June 23, 2023
Wednesday, June 21, 2023
Saturday, June 17, 2023
Tuesday, June 13, 2023
Friday, June 9, 2023
Saturday, June 3, 2023
Subscribe to:
Posts (Atom)
Most watched
-
Quick answer: Qwen 3 32B needs about 22.7 GB of VRAM at Q4_K_M with a 4k-token context — a used 24 GB card like the RTX 3090 is the minimu...
-
Using GPUs in TensorFlow, TensorBoard in notebooks, finding new datasets, & more! (#AskTensorFlow) [Collection] In a special live ep...
-
Inside TensorFlow: Summaries and TensorBoard [Collection] Take an inside look into the TensorFlow team’s own internal training sessions-...
-
Quick answer: For an 8B model at Q4, local electricity costs roughly $0.05 per million output tokens — against about $0.53 per million ble...
-
Quick answer: For machine-learning work, buy an external SSD over a spinning hard drive, pick USB 3.2 Gen 2 (10 Gbps) or faster, and size f...
-
Quick answer: DeepSeek V4 Flash is a Mixture-of-Experts model: all 284 billion parameters must be stored, so combined RAM plus VRAM — not ...
-
Quick answer: Yes, for most budget builders: a used RTX 3090 is still the cheapest route to 24 GB of VRAM with full CUDA support. Capacity...
-
Hey everyone This is Ujjwal kapil B.tech 2nd year Ai and Ml In this video we covered one of the most important question "COLLEGE KAB O...
-
Quick answer: The cheapest path to serious local-AI VRAM is not one new flagship card — it is two used ones. A single RTX 5090 costs $1,999...
-
Quick answer: FLUX.1 dev needs about 10 GB of VRAM at Q4/NF4 quantization for 1024×1024 image generation, so a 12 GB GPU such as the GeFor...
