Contribute
Contribute to Tokenstead
Local AI is built by the people running it.
Every rig, benchmark, and guide here started as something a reader sent in. Corrections, price reports, and tool tips need no account. Everything lands in a moderator queue before it reaches a page.
Ways to contribute
Pick the one that matches what you have. Each opens a form built for that kind of data.
01 / Rigs
Share your rig
Parts, photos, and the real tok/s. Your build becomes the fit math someone else uses to decide.
Share your rig →02 / Benchmarks
Submit a benchmark
A measured run on hardware you own. Attach the model, the quant, the settings, and the numbers.
Submit a benchmark →03 / Guides
Write a guide
What you built, what broke, and what you would do differently. A human reviews every submission before it publishes.
Start a guide →04 / Corrections
Send a correction
Wrong number, stale step, dead link. Send the page and the correction; a moderator checks it against the source.
Send a correction →05 / Prices
Report a price
A provider price that moved, or an invoice that does not match the list page. Send the date and the line item.
Report a price →06 / Tools
Suggest a tool or harness
A harness, CLI, or local UI you run. Tell us what it does, what it costs, and where it breaks.
Suggest a tool →07 / Policy
Flag a policy change
A rule that changes what you can download, run, or ship. Link the primary document and say who it hits.
Flag a policy change →Open calls
Concrete things we are missing right now. Pick one and send what you have; a partial answer still helps.
-
Benchmark request Open call 01
DeepSeek V4 Flash on a 24GB desktop card
The 128GB unified-memory numbers are in. A clean q4_k_m run on a single 24GB card, with prompt processing and the context length you used, is not.
-
Price report Open call 02
Your last hosted invoice for an open-weight model
List prices and billed prices drift once caching and batch discounts land. Send the provider, the line item, and the date on the invoice.
-
Correction Open call 03
A guide step that no longer works
Runtimes, quants, and flags move. If a setup step on a guide failed for you this month, send the page and the error text.
-
Tool or harness Open call 04
The harness you actually drive every day
Name the harness, the model behind it, and the failure that made you switch. We are building the harness catalog from people who run one for real.
-
Rig Open call 05
A two-card rig that earns the second card
Tok/s before and after the second GPU, plus the interconnect and the workload. The per-watt math is the part most build logs skip.
-
Policy tip Open call 06
A rule change with a date and a primary source
Export controls, license terms, data-center rules. Link the document and say what changes for someone running models at home.
-
Guide pitch Open call 07
A build log with the part that did not fit
The return you ate, the riser that did not clear the case, the BIOS setting that saved the boot. That detail saves someone a weekend.
-
Speech Open call 08
A 24GB Nemotron Transcribe run
NVIDIA's 34B speech model ships NVFP4 and GGUF. Run one hour of overlapping audio on a 24GB card with NeMo-Speech.cpp or vLLM and report peak VRAM, seconds of audio per second, speaker and timestamp quality, and WER on your sample.
-
Source check Open call 09
Date the GLM-5.5 lecture slides
A viral post attributes a six-source data pipeline and 32B/122B/256B sizes to a Jie Tang talk this week. The photographed slide footer reads Tsinghua, 2024 InterTalk, and Z.ai has no public GLM-5.5 model card. Find the recording or the official deck and send the date and link.
-
Models Open call 10
A small model that replaced a big one
If a 12B model took over a 70B workload, show the prompt, the output, and the hardware it ran on.
Recent contributors
The latest bylined work from the community. Every one of these is live on the site.
@placeholder-niklaslenz-ai shared a rig
Rig4x DGX Spark 15U rack - Niklas
cdnsteve shared a rig
Rig8x RTX 3090 open frame - AxiTek
cdnsteve published a guide
GuideAlibaba Cloud puts $3M into Omarchy and names it the OS target for Qwen Book, an ARM-first agentic computer
Tobi Lutke shared a rig
RigJeffrey Guenther Rack Cellar
Tobi Lutke shared a rig
RigTobi Lutke Rack Cellar
@placeholder-typecraft-dev shared a rig
RigTypecraft's homelab
cdnsteve shared a rig
RigRyzen AI Max 395+ / Radeon PRO R9700 lab - Martin Mielke
cdnsteve logged a benchmark
BenchmarkDeepSeek V4 Flash 0731 on GB10 (DGX Spark)
cdnsteve published a guide
GuideRun the Grok CLI on Ollama Cloud and custom providers
Start somewhere small
A correction takes two minutes and saves the next reader a dead end. If you would rather write the whole thing, the guide editor is one click away. If you built something and have numbers, the rig and benchmark forms take the raw data.