more pics from the Tenstorrent lab of my > 4x QuietBox Blackhole Cluster by the time i receive them in a few weeks > 7 NEW MoE architectures will be SUPPORTED specs of each QuietBox: > EPYC 8124P (16C/32T, 3 GHz)
> 512 GB DDR5-4800 ECC RDIMM > 4x Blackhole p150c: 128GB VRAM
@theahmadosman
-
Tenstorrent QuietBox Blackhole Cluster specs and MoE support
By
–
-
Qwen Releases S Tier Lab Model with Advanced Features
By
–
Qwen are playing to win S Tier lab awesome model in both size and features
-
Superflower 1600W PSU Recommendation for AI Infrastructure
By
–
soon tm for PSUs, i highly recommend the Superflower 1600w units tier a
-
Training AI Models at Home: Infrastructure Limitations and Feasibility
By
–
building your own model from scratch, including the full training process, isn't feasible with a home setup
-
SSD Performance Advantages for AI Model Loading Speed
By
–
Also, 4tb ssd, same model would be HDD loading speeds are awful, especially for hot swapping big models
-
Merit Over Bias: Hard Work Transcends Borders and Prejudice
By
–
i know some people are gonna hate me for this, but: hard work doesn’t care where your parents were standing on the map when you were born. if you’re really as good as you say you are,
you don’t need to be hateful, racist, or xenophobic. kindness costs nothing. -
DGX Spark Downgraded: Poor Value Proposition Analysis
By
–
DGX Spark – Ahmad's Analysis > downgraded to no buy > 2× the cost of a 5090 for ~30% FP4 perf > crippled bandwidth (273 GB/s, worse than a MacBook Pro)
-
GPU Setup Discussion: Addressing Critic Concerns and Hardware Research
By
–
i hear the critics, and even then, i am glad some are doing their research and learning what they need and what they don't in terms of GPUs if you have "specific" questions about my setup, i am open to answering them otherwise, keep learning, and maybe Buy a GPU or two 🙂
