#RunPod
まほうしょうじょ⭐️あやなちゃん
#AIイラスト #ComfyUI
November 9, 2026 at 2:44 PM
起きたら昼だったぷり
\(^o^)/

#AIイラスト #ComfyUI
November 9, 2026 at 3:40 AM
November 9, 2026 at 5:45 PM
November 7, 2026 at 11:22 AM
くりす「急にSNSやるのが面倒になる時って、あるのよね」
#AIイラスト #ComfyUI
November 7, 2026 at 10:56 AM
RunPod: Kimi K3 runs on a single 8xB300 Pod on Runpod at $71.92/hr, 128K context
November 10, 2026 at 12:45 AM
RunPod Pods vs Serverless GPU (vLLM / H100 / A40) & Batch Inference (-30%) Break-Even Calculator

At what daily token volume do Dedicated GPU Pods (H100 / A40 / L40S via vLLM) beat Serverless Endpoints? Includes Nov 2026 RunPod Serverless Batch Inference GA (-20% to -30% off H100/H200/B200), Ki...
November 9, 2026 at 6:45 PM
November 8, 2026 at 5:28 PM
November 7, 2026 at 10:25 PM
And they stole my $10. #Collab is a useless piece of garbage for #video generation. Your #AI will lie to you. It ran out of my #Gemini credits for the day before it could even get #ComfyUI set up one time. 🤦🏻‍♀️🤦🏻‍♀️🤦🏻‍♀️ I'm trying #Runpod.
High-end video from #MissKitty's visual creations is quite the setup. Headless #virtual #machines in the cloud. I'm swimming in waters I understand but I do not recognize all the fish. LOL Some might be sharks. I hate that I had to hug the beast again. Until I know more. #Github #ComfyUI #Colab
November 7, 2026 at 12:49 PM
November 10, 2026 at 1:16 AM
くりす「いろいろおかしい、ですって?」
#AIイラスト #ComfyUI
November 7, 2026 at 11:50 PM
November 7, 2026 at 3:32 PM
Runpod Hub live: deploy open-source AI repos including ComfyUI, Whisper, Mochi 1
November 6, 2026 at 3:30 PM
November 4, 2026 at 12:34 AM
DeepSeek R1 Q4 runs on Runpod with 480GB VRAM at $10.74/hr on 6xA100s.
November 10, 2026 at 1:15 AM
RunPod Pods vs Serverless GPU (vLLM / H100 / A40) & Batch Inference (-30%) Break-Even Calculator

At what daily token volume do Dedicated GPU Pods (H100 / A40 / L40S via vLLM) beat Serverless Endpoints? Includes Nov 2026 RunPod Serverless Batch Inference GA (-20% to -30% off H100/H200/B200), Ki...
November 9, 2026 at 1:15 AM
#Runpod is such garbage. I used so many different servers underneath so many different #ComfyUI configs. Spent whole day losing my ever-loving shit behind how awful these image to video sites are. Nobody is doing an unfiltered good job. #Midjourney is great but their filters are over the top.
RunPod is a much better fit for that — use a prebuilt ComfyUI template so you're not paying to install, and set auto-stop. Idle pods keep billing while you troubleshoot, which is exactly what we warn about at coreforgemeter.com.
November 8, 2026 at 4:32 AM
RunPod: Flash CLI now ships a Nix flake: nix run github:runpod/flash
November 6, 2026 at 4:00 PM
1/ The Core Unit Economics Bottleneck (Infrastructure Break-Even):
• Unoptimized frontier LLM calls, uncached system prompts & multi-turn context growth silently erode SaaS gross margins from 80% down to <35%.
• Focus area: self hosted llm vs api cost calculator vllm h100 runpod pods vs serverl...
November 9, 2026 at 6:46 PM
まだ寝ないぷり
12枚綴りをイロミライとかに置いたぷり

寝るぷりのさとみん #33 - あかりの日 【R-15】 12枚
iromirai.jp/posts/617285...

#AIイラスト #ComfyUI #イロミライ
November 9, 2026 at 11:30 AM
November 3, 2026 at 2:34 AM
GPU Pods vs Serverless + Batch Inference (-30%) Break-Even Math:

• RunPod Serverless Batch GA cuts async H100/H200/B200/A40 eval & backfill spend by 20%–30%
• Kimi K3.1 Pro (3T MoE, 1M context): $2/$10 per 1M
• ⚠️ Nov 15: RunPod REST API v1 shuts down (migrate to v2) #AI #LLM #FinOps
November 5, 2026 at 1:28 AM
Cheapest GPU rentals today (2026-11-10), by VRAM:
32GB Tesla V100 $0.069/h (Vast.ai)
48GB RTX A6000 $0.330/h (RunPod)

RTX 4070S Ti ▲115% vs yesterday, now $0.203/h
RTX A4500 ▲74% vs yesterday, now $0.190/h

All chips, 90-day history: https://overfeed.news/gpus
#GPU #AI #LLM
November 10, 2026 at 12:02 AM