Nick K. PRO

hexgridcloud

·

https://hexgrid.cloud

AI & ML interests

One-click deployment of Open-source LLMs, on managed and dedicated GPUs.

Recent Activity

upvoted an article 17 days ago

Kimi K3 Is 2.8T Parameters. That’s Not the Hardest Part of Serving It.

published an article 17 days ago

Kimi K3 Is 2.8T Parameters. That’s Not the Hardest Part of Serving It.

new activity 17 days ago

zai-org/GLM-5.2:I researched the practical GPU specs for GLM-5.2 — a few findings that surprised me more...

View all activity

Organizations

New activity in zai-org/GLM-5.2 17 days ago

I researched the practical GPU specs for GLM-5.2 — a few findings that surprised me more...

#62 opened 17 days ago by

New activity in moonshotai/Kimi-K3 17 days ago

I researched the practical GPU specs for Kimi-K3 — a few findings that surprised me more...

#171 opened 17 days ago by

New activity in Qwen/Qwen3.8-2.4T-A95B 19 days ago

I researched the practical vLLM configs for Qwen3.8-2.4T-A95B — a few findings that surprised me more...

#35 opened 19 days ago by

New activity in google/gemma-4-31B-it 2 months ago

Benchmarked on HexGrid Cloud : Gemma-4 31B + vLLM + RTX 6000 PRO : 1168 tokens/sec and still asking for more...

#123 opened 2 months ago by

New activity in Qwen/Qwen3.5-9B 2 months ago

Deployed on HexGrid Cloud: 1x RTX 5090 + Qwen3.5 9B BF16 — 1280 tok/s peak, then TTFT goes from 0.7s to 18s, ShareGPT, concurrency 16–128

#58 opened 3 months ago by

New activity in Qwen/Qwen3.5-9B 3 months ago

Deployed on HexGrid Cloud: 1x RTX 5090 + Qwen3.5 9B BF16 — 1280 tok/s peak, then TTFT goes from 0.7s to 18s, ShareGPT, concurrency 16–128

#58 opened 3 months ago by