Modal Blog - Plushcap

Blog URL

modal.com/blog

Posts YTD

5 ↓ vs 7 last year

Avg Posts/Month

1.3 since 2022

Monthly Post Volume

Start year: 2024 2025 2026

Post Details

Search:

Title	Author	Published	Words	HN Pts
What is Flux Dev?	Kenny Ning	2024-10-17	469	--
Top open-source text-to-speech libraries in 2025	Yiren Lu	2025-03-10	876	--
How Modal speeds up container launches in the cloud	Yiren Lu	2024-08-16	1,082	--
Top embedding models for RAG	Yiren Lu	2024-10-30	557	--
A1111 vs ComfyUI	Kenny Ning	2024-08-23	640	--
RabbitMQ vs. Kafka: choosing the right messaging system	Yiren Lu	2024-09-25	920	--
How Contextual AI automated CI with Modal GPUs	-	2024-09-18	740	--
Google Cloud Run vs. Cloud Run Functions: understanding Google's serverless offerings	Yiren Lu	2024-09-25	757	--
How OpenArt scaled their Gen AI art platform on hundreds of GPUs	-	2024-11-20	620	--
A10 vs. A100 vs. H100 - Which one should you choose?	Yiren Lu	2025-01-27	844	--
Why Substack moved their AI and ML pipelines to Modal	-	2024-05-20	453	--
Best open-source LLMs in 2025	Yiren Lu	2025-03-10	1,344	--
Fast, lazy container loading in Modal.com	Jonathan Belotti	2024-09-08	2,582	--
How Suno shaved 4 months off their launch timeline with Modal	-	2024-02-21	509	--
Open-source AI agents	Kenny Ning	2024-09-23	692	--
Build interactive workflows using Kestra and Modal	Anna Geller	2024-10-15	1,883	--
Introducing: Region selection	-	2024-05-13	481	--
Inside the Modal Code Playground	Rachel Park	2024-08-16	672	--
How Ramp automated receipt processing with fine-tuned LLMs	-	2024-03-26	517	2
Google Cloud Run functions pricing: understanding costs and optimization	Yiren Lu	2024-09-25	742	--
Batch processing vs. stream processing by example	Yiren Lu	2024-09-04	615	--
Dogfooding Modal: What we learned at our internal hackathon	-	2024-12-09	611	--
WireGuard at Modal: Static IPs for Serverless Containers	Eric Zhang	2024-12-02	3,035	125
How to get GPUs with a Jupyter notebook on Modal	Yiren Lu	2024-09-15	261	--
Introducing: L40S GPUs on Modal	-	2024-12-19	466	--
Beating Proprietary Models with a Quick Fine-Tune	Jason Liu	2024-04-26	2,384	6
Stable Diffusion 3.5 vs. Flux	Yiren Lu	2024-11-02	643	--
How to deploy code in AWS Lambda: the easy way for beginners	Yiren Lu	2024-09-14	752	--
How to deploy a Gradio app	Yiren Lu	2024-09-15	632	--
Run GPU jobs from Airflow with Modal	Kenny Ning	2024-06-20	1,664	2
Best practices for serverless inference	Yiren Lu	2024-09-25	636	--
How to run Ollama	Yiren Lu	2024-09-15	537	--
How to run XTTS	Yiren Lu	2024-09-15	460	--
How to run Llama 3.1 as an API	Kenny Ning	2024-09-18	396	--
What is Flash Attention?	Yiren Lu	2024-10-16	627	--
Glossary: LLM fine-tuning hyperparameters	Yiren Lu	2024-10-15	681	--
All the open-source Whisper variations	Yiren Lu	2024-08-15	703	--
How much VRAM do I need for LLM model fine-tuning?	Yiren Lu	2024-09-01	393	--
vLLM vs. TGI	Yiren Lu	2024-10-15	541	--
ChatTTS: Running an open source text-to-speech model	Yiren Lu	2024-09-15	498	--
Llama3-405B: How to run an extra large open source LLM on Modal	Yiren Lu	2024-09-15	515	--
Upload files to S3 with AWS Lambda and AWS API Gateway in …	Yiren Lu	2024-09-04	640	--
How a top tier European soccer team sped up their data processing …	-	2024-12-04	525	--
Fine-tuning vs. RAG	Yiren Lu	2024-10-15	1,523	--
How much VRAM do I need for LLM inference?	Yiren Lu	2024-09-01	261	--
Top ComfyUI custom node packs	Kenny Ning	2024-11-12	874	--
Embedding English Wikipedia in under 15 minutes	Jason Liu	2024-01-23	2,433	7
Top embedding models on the MTEB leaderboard	Yiren Lu	2025-01-27	701	--
Top 5 serverless GPU providers	Yiren Lu	2024-09-27	857	--
How much is an Nvidia H100?	Yiren Lu	2024-08-15	531	--
AWS Lambda vs. Google Cloud functions: a comprehensive comparison	Yiren Lu	2024-09-25	853	--
How much is an Nvidia A100?	-	2024-10-31	794	--
Top open-source text-to-video AI models	Yiren Lu	2024-10-30	563	--
Best frameworks for fine-tuning LLMs in 2025	Yiren Lu	2025-01-27	614	--
Create an infinite icon library by fine-tuning Stable Diffusion	Yiren Lu	2024-05-21	2,435	--
How to run cron jobs	Kenny Ning	2024-04-30	681	--
Create a custom video generator by fine-tuning a Mochi LoRA on Modal	-	2024-11-26	640	--
Building a cost-effective analytics stack with Modal, dlt, and dbt	Kenny Ning	2024-09-10	2,487	--
Modal is SOC 2 Type II Compliant	-	2025-01-02	216	--
Top image segmentation models	Yiren Lu	2024-10-30	648	--
Dagster vs. Airflow: a comprehensive comparison	Yiren Lu	2024-09-25	767	--
LoRA vs. QLoRA: Efficient fine-tuning techniques for LLMs	Yiren Lu	2024-08-22	757	--
How Reducto improved enterprise-scale document processing latency by 3x	--	2025-11-19	803	--
Host overhead is killing your inference efficiency	Charles Frye, Nathan Wang, Timothy Feng	2025-11-18	1,605	3
Product Updates: Updates to Volumes, JS and Go SDKs, and more	--	2025-10-31	546	--
One-Second Voice-to-Voice Latency with Modal, Pipecat, and Open Models	Ben Shababo	2025-11-04	2,683	3
How Decagon shipped real-time voice AI on Modal	Richard Gong, Timothy Feng, Cyrus Asgari	2025-11-13	890	--
How Zencastr transcribed hundreds of years worth of audio in just a …	--	2025-08-28	916	--
Modal + Datalab: Deploy high-throughput document intelligence in <5 minutes	--	2025-10-29	811	--
Modal + Mistral 3: 10x faster cold starts with GPU snapshotting	--	2025-12-02	521	--
Agents need good developer experience too	Michael Waskom, Rebecka Storm	2025-11-20	104	3
How to achieve truly serverless GPUs	Charles Frye, Jonathan Belotti, Erik Bernhardsson, Akshat Bubna	2026-05-12	4,960	4
Modal's Series C: Raising $355M at a $4.65B valuation	--	2026-05-21	1,015	2
Introducing Modal Auto Endpoints: Optimized inference you actually own	--	2026-06-23	1,524	19
Inkling by Thinking Machines now available on Modal	--	2026-07-15	647	--
Kimi K3 by Moonshot now available on Modal	--	2026-07-27	558	4

Plushcap, by Matt Makai. 2021-2026.