# Fireworks Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/fireworks
> Markdown URL: https://aitinkerers.org/technologies/fireworks.md
> Technology record last updated: 2026-04-18T01:24:01Z
> Generated: 2026-09-22T03:57:40Z

Fireworks is the high-performance, cloud-native inference platform for production-scale generative AI (GenAI), delivering ultra-low latency and high throughput for open-source models.

This is the platform for serious GenAI deployment: Fireworks provides a highly optimized, serverless infrastructure for running, fine-tuning, and scaling open-source Large Language Models (LLMs). We're talking about real performance gains—up to 4x higher throughput and 4x lower latency than standard open-source setups (running on NVIDIA H100/A100 GPUs). Developers get instant access to a massive library of models (including LLaMA, Mixtral, and DBRX) with a single API call, abstracting away the complexity of GPU management. The focus is 'Compound AI': using the best model for each sub-task to solve enterprise problems like code assistance and complex agentic systems with speed and cost-efficiency.

- Official technology site: https://fireworks.ai
- Public AI Tinkerers demos and talks: 3
- Result page: 1 of 1

## Recent Public Talks and Demos

### [ZameenEye AI & AgentOS: Spatial Climate Risk & Personal Agentic OS](https://mombasa.aitinkerers.org/talks/rsvp_3azR3jXQt5Y)

dual-part technical demonstration featuring ZameenEye AI (a four-layer satellite-to-advisory climate risk mapping system using PostGIS ST_Intersects and Llama-3-70B) alongside AgentOS (a 24/7 headless personal agentic OS running on a DigitalOcean droplet with multi-channel routing and strict guardrails).

- Event context: AI Tinkerers – Mombasa Chapter Launch · 22 August 2026 — 2026-08-22 — Mombasa
- Public talk page: https://mombasa.aitinkerers.org/talks/rsvp_3azR3jXQt5Y

### [Watch 1 hour highly techincal YouTubes in 5 minutes with AI!](https://seattle.aitinkerers.org/talks/rsvp_cjwx88z4AkE)

AG is an agent that watches YouTube podcasts for you so you know which ones to really dig into. With AG, see in 5 minutes a summary of the YouTube, key quotes, see key blackboard / slide / code sections, jump around key passages, and decide if you should spend the full time on the video. Break down highly techincal episodes from Dwarkesh, Lenny, AI Engineer, and more!

- Event context: AI Tinkerers Seattle Summer Bash — 2026-07-29 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_cjwx88z4AkE

### [Fine Tune and Evaluate 10 LLMs in in 10 minutes](https://toronto.aitinkerers.org/talks/rsvp_UtPaqTCgvXU)

I'll be starting from scratch, and demoing the process of fine-tuning and evaluating our own LLM models. Steps in demo: - Generating synthetic data for training - Fine-tuning a range of open models (Gemma 3, Qwen3, Llama 3/4) - Using LLM-as-Judge and G-Eval evals to figure out which fine-tune performs the best for our task Interesting points I'll cover throughout the demo: - Who evaluates the eval? Methods of baselining evals to human preference. - How to collaborate on datasets using git - Writing custom evals - Performance and cost benefits of fine-tuning - Privacy benefits of fine-tuning - Pros and cons of remote GPU (cloud) vs local for both training and inference - Fine-tuned distillations: can they outperform the original model on task specific evals? (yes, sometimes!)

- Event context: AI Tinkerers Toronto - June 2025 Meetup at NEXT Canada -- sponsored by Intel AI! — 2025-06-18 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_UtPaqTCgvXU

## Related Technologies

- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [Claude](https://aitinkerers.org/technologies/claude) ([Markdown](https://aitinkerers.org/technologies/claude.md)) — 174 public demos
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [GPU](https://aitinkerers.org/technologies/gpu) ([Markdown](https://aitinkerers.org/technologies/gpu.md)) — 12 public demos
- [Inference](https://aitinkerers.org/technologies/inference) ([Markdown](https://aitinkerers.org/technologies/inference.md)) — 9 public demos
- [Kiln](https://aitinkerers.org/technologies/kiln) ([Markdown](https://aitinkerers.org/technologies/kiln.md)) — 1 public demo
- [Llama 3 70B](https://aitinkerers.org/technologies/llama-3-70b) ([Markdown](https://aitinkerers.org/technologies/llama-3-70b.md)) — 3 public demos
- [Modal](https://aitinkerers.org/technologies/modal) ([Markdown](https://aitinkerers.org/technologies/modal.md)) — 14 public demos
- [NVIDIA NIM](https://aitinkerers.org/technologies/nvidia-nim) ([Markdown](https://aitinkerers.org/technologies/nvidia-nim.md)) — 1 public demo
- [OpenAI](https://aitinkerers.org/technologies/openai) ([Markdown](https://aitinkerers.org/technologies/openai.md)) — 112 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [PostGIS](https://aitinkerers.org/technologies/postgis) ([Markdown](https://aitinkerers.org/technologies/postgis.md)) — 6 public demos
- [PostgreSQL](https://aitinkerers.org/technologies/postgresql) ([Markdown](https://aitinkerers.org/technologies/postgresql.md)) — 106 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [unsloth](https://aitinkerers.org/technologies/unsloth) ([Markdown](https://aitinkerers.org/technologies/unsloth.md)) — 8 public demos