Top all-time · #9871
Runpod
Company blog · blog.runpod.io/blogaihardware
Runpod is the company blog at blog.runpod.io, writing about ai and hardware. Since 2023, 8 different Hacker News readers have linked it 10 times, most often “AMD MI300X vs. Nvidia H100 LLM Benchmarks”. It is still writing: the last post was on 2026-11-01, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link Runpod content on running LLMs locally, including estimating the VRAM a model needs. The comments discuss that topic and GPU throughput but do not judge the writing.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
The Runpod blog: AI infrastructure guides, GPU tutorials, model deployment patterns, and product updates for developers building on Runpod.
Most-linked posts?
- AMD MI300X vs. Nvidia H100 LLM Benchmarks3 people · 3 mentions · first linked 2024-07-01
What Hacker News says?
This is a tough question to answer, because it depends a lot on what you want to do! One way to approach it may be to look at what models you want to run and check the amount of VRAM they need. A back-of-the-napkin method taken from here[0] is: VRAM (GB) = 1.2 * number of parameters (in billions) * bits per parameter / 8 The 1.2 is just an estimation factor to account for the VRAM needed for things that aren't model…
Comment linking /understanding-vram-and-how-much-your-llm-needs/
on “Llama.vim – Local LLM-assisted text completion”Submitted AMD MI300X vs. Nvidia H100 LLM Benchmarks as a story · 13 points
HN discussionrelative to what? according to this, a single card is capable of >300t/s on Mistral-7B and the workstations with 4 cards are doing nearly 500t/s on Mixtral-7Bx8. yeah the H100 and MI300 nearly 10x those numbers [1] at the same batch sizes, but those cards are unobtainium server-class hardware priced way outside the prosumer range. while these cards cost less than a RTX 4090 and only use ~300W. what other options exi…
Comment linking /amd-mi300x-vs-nvidia-h100-sxm-performance-comparison-on-mixtral-8x7b-inference/
on “Tenstorrent Unveils High-End Wormhole AI Processors, Featuring RISC-V”Submitted Instant Clusters: Multi-Node AI Compute in Minutes as a story · 8 points
HN discussionSubmitted Nvidia H100 vs. AMD MI300X as a story · 4 points
HN discussionSubmitted Easily run SAM2 on GPU cloud as a story · 3 points
HN discussionSubmitted The Beginner's Guide to Textual Worldbuilding with Oobabooga and Pygmalion as a story · 3 points
HN discussionSubmitted The Effects of Rank, Epochs, and Learning Rate on Training Textual LoRAs as a story · 2 points
HN discussionSubmitted Cogito Trained High-Performance Open Models on the Path to ASI as a story · 1 points
HN discussionSubmitted Learning AI Without Code: A Marketer's Journey into ML Concepts as a story · 1 points
HN discussion