TL;DR
Odysseus — PewDiePie's open-source AI workspace — publishes no official hardware requirements — and its own docs explain why. The app is lightweight; what's heavy is the local model you serve behind it, and that depends on model size × quantization × free memory. Every "Odysseus system requirements" table on third-party sites is unofficial. The honest path: measure your hardware in 15 seconds, then match the result to the model class you want to run. In API mode, Odysseus runs on almost anything.

Since Odysseus hit 84,000+ GitHub stars, "can my PC run Odysseus" has become an autocomplete query — and the top results answer it with requirement tables that the Odysseus project never published. This article does it the honest way: what the official docs actually say (with sources), what genuinely decides whether your machine can handle it, and how to measure that in your browser before you install anything.

What Odysseus is (in 60 seconds)

Odysseus is an open-source, self-hosted AI workspace: chat, agents, research, documents, email, notes, and calendar in one locally-run app, licensed AGPL-3.0. It was started by Felix "PewDiePie" Kjellberg and is now developed in the open at github.com/odysseus-dev/odysseus. The point of self-hosting: your data stays on your machine, and you decide which AI models do the work.

For the "can my PC run it" question, one architectural fact matters more than anything else: Odysseus doesn't run AI models itself. It connects to a model backend — Ollama, llama.cpp, vLLM, or SGLang for local models, or cloud APIs if you'd rather not run models locally at all. So the real question is never "can my PC run Odysseus" — it's "can my PC serve the model I want behind Odysseus."

The truth: there are no official requirements

The official setup guide addresses hardware in exactly one general sentence:

"The app itself is lightweight; local model serving is the heavy part and depends on the model, runtime, GPU, and VRAM, so small hosts can connect to API or remote model servers instead." docs/setup.md, Odysseus repository

That's it. No minimum-spec table, no "recommended: 16 GB RAM", no tiers. The hardware question in the project's own discussions (#274, open since June 2026) has no official spec answer — the only project-team reply is a single-GPU anecdote, and the community replies disagree with each other, because the honest answer really is "it depends on the model you pick."

About those requirement tables elsewhere: several third-party sites publish detailed "Odysseus system requirements" — minimum CPU, recommended VRAM, the works. None of them are affiliated with the project, and the numbers don't trace back to anything in the Odysseus repository. If a spec table isn't on github.com/odysseus-dev/odysseus or odysseus-dev.github.io/odysseus, it's someone's guess.

The one official sizing sentence

The setup guide does contain a single concrete piece of sizing advice:

"For first-time local model testing on 8 GB laptop GPUs, start with GGUF/Q4 models on llama.cpp before trying GPTQ/AWQ models on vLLM or SGLang." — docs/setup.md, Odysseus repository

Translated: if you have a mainstream gaming laptop (RTX 4060 class, 8 GB VRAM), the project itself points you at 4-bit-quantized GGUF models served by llama.cpp. That's the entry door — and it's exactly the model class we test against below.

What actually decides: model × quantization × memory

Whether a local model runs on your machine comes down to arithmetic, not app specs. A model's weights have to fit in memory (VRAM, unified memory, or system RAM with CPU offload), plus working space for the KV cache. Quantization shrinks the weights: a 7-billion-parameter model at Q4 (4-bit) is roughly 4 GB of weights — per the llama.cpp quantization docs — where the same model at FP16 would be ~14 GB.

Rough memory math for the model classes most people serve behind Odysseus (weights + typical KV cache, Q4 GGUF):

Model classApprox. memory neededTypical hardware that clears it
7B Q4 (Llama, Qwen, Mistral class)~6 GB freeMost 2022+ laptops with dGPU; 8 GB VRAM cards; M-series Macs
13B Q4~10–11 GB free16 GB RAM laptops (unified/offload), 12 GB+ VRAM GPUs
32B Q4 (coder models)~22 GB free24 GB VRAM GPUs, 32 GB+ unified memory Macs
70B Q4~40+ GB freeWorkstations, 64 GB+ RAM, Ultra-tier Apple Silicon

⚠ This is model math derived from llama.cpp/Ollama documentation — not an official Odysseus spec. Odysseus publishes no such table.

Odysseus's own hardware-fit logic agrees that headroom is what matters. Its hwfit service (as of July 2026) labels a GPU fit "perfect" when VRAM is at least 1.5× the model's requirement and "good" at 1.2× — below that, "marginal." In other words, the project's own code treats memory headroom as the deciding factor. That's a moving target (the constants can change), but the principle — measure your memory headroom before picking a model — is stable.

Measure it in 15 seconds (before you install anything)

Odysseus ships a built-in hardware scanner (the Cookbook) that recommends models from a 270+ model catalog — but it only works after you've installed the whole stack. If you want the answer before committing to Docker, WSL2, and a multi-gigabyte setup, that's what 9bench is for: a 15-second browser test, no install, no account.

What it gives you, kept honest by separating two kinds of numbers:

There's also an optional live LLM test that downloads a small model and runs real inference in your tab. That number is measured, not estimated — but note it's a browser number: native llama.cpp on the same machine typically runs 5–10× faster. Treat the live test as a lower bound and a reality check, not as a prediction of Odysseus performance.

▶ Test my hardware (15 seconds)

Reading your result for Odysseus

Your 9bench result page shows per-model verdicts (Llama 7B/13B/70B Q4 GGUF, and more) for both browser and native execution. Here's how they map to Odysseus:

Install reality check (the part spec tables never mention)

Hardware capability is necessary but not sufficient — the installation path has real platform caveats, straight from the project's docs and issue tracker:

Honesty footnotes: 9bench is not affiliated with Odysseus, its maintainers, or PewDiePie. Browser measurements are not native performance — native llama.cpp typically runs 5–10× faster than in-tab inference, which is why estimated native values are labeled as estimates everywhere they appear. The live in-browser tokens/s is a measured lower bound, not an Odysseus performance prediction. Odysseus's fit-logic constants (1.2× / 1.5×) are as of July 2026 and may change; the memory-math table above is derived from llama.cpp/Ollama documentation, not from the Odysseus project.

The 15-second answer

Nobody can tell you "Odysseus needs X" — the project itself doesn't. But your machine can tell you what model class it serves. Measure it, match it, then install.

▶ Test my hardware (15 seconds)