← Dashboard
TheAhmadOsman

Ahmad ✓

52.2K followers
3 tweets
Communities: x/LocalLLaMA
# Tweet Community Topic Views Ratio Engagement Posted
1
[image] Just some numbers so you don’t get misled RTX 3090 (7 years old) > 24GB VRAM > Bandwidth: 936.2 GB/s > Bi-directional NVLink 112GB/s RTX PRO 4000 > 24GB VRAM > Bandwidth: 672 GB/s > No Bi-directional NVLink, > need 32 Gen. 5 PCIe Lanes to pool 2 at 64GB/s
x/LocalLLaMA Artificial Intelligence 42.1K 0.8x 286 Apr 6
2
[image] How am I connecting the DGX Spark cluster > Mikrotik CRS804-4DDQ 1.6Tbps switch > (4) 400G QSFP-DD to 2x 200G QSFP56 Each DGX Spark has a ConnectX-7 supporting 200Gbps Each cable out of the switch goes into 2 DGX Sparks This allows 8x DGX Sparks cluster at the full 1.6Tbps
x/LocalLLaMA Artificial Intelligence 33.0K 0.8x 214 Feb 19
3
[text] Most people think VRAM = model size and that’s why their runs crash GPU memory math is complex and so are the implications Here’s how it actually works in a nutshell ↓
x/LocalLLaMA Artificial Intelligence 23.7K 0.5x 239 Apr 3
4
[image] which one of you is this?
x/LocalLLaMA Artificial Intelligence 12.1K 0.2x 235 Apr 2
5
[image] RTX PRO 6000 (96GB VRAM, ~$15K) GIVEAWAY FAQ Q: Cost to enter? A: $0. Free. Q: Do I have to register for GTC? A: Yes, virtual attendance is COMPLETELY FREE Q: Where do I enter? A: Tap the link in my bio, there’s a clear button on the page Q: How do I increase my chances? A:
x/LocalLLaMA Artificial Intelligence 9.5K 0.2x 89 Mar 7