(on now)

Run AI models on your own hardware.

Find what to run, what to run on it, what it costs, and who to follow.

Checked 2026-10-10 · every page is read against the data behind it, and the date is printed with it

What fits in 24 GB

Full calculator →

Weights at Q4_K_M: the largest models that fit in 24 GB are below. Add room for the context: the VRAM calculator does the full sum for your cards. Fitting is not running — the engine floors check the card against the minimum each engine publishes.

chat

Qwen3.6-35B-A3B

21 GB of weights at Q4_K_M

Alibaba · 35B MoE, 3B active · Apache 2.0

video

MiniMax-H3

20 GB of weights at Q4_K_M

MiniMax · 33B dense · MiniMax H3 Community Licence

chat

Qwen3 32B

20 GB of weights at Q4_K_M

Qwen · 32.76B dense · Apache 2.0

chat

Gemma 4 31B

19 GB of weights at Q4_K_M

Google · 31B dense · Apache 2.0

chat

Qwen3 30B A3B Instruct 2507

19 GB of weights at Q4_K_M

Qwen · 30.53B MoE, 3.3B active · Apache 2.0

code

Qwen3 Coder 30B A3B

19 GB of weights at Q4_K_M

Qwen · 30.53B MoE, 3.3B active · Apache 2.0

Next on the calendar

All events →

People and channels

All people and channels →

From the garage

All rigs →

Rig measurements

The leaderboard →
RigGPUsModelEnginepp512 t/stg128 t/sWall WDate
An RTX 3090 on a 32-core ThreadripperNVIDIA RTX 3090 24 GBQwen3-30B-A3B
Qwen3-30B-A3B-Q4_K_M.gguf
llama.cpp b10002 (a7312ae)4232207.6–2026-10-10
A Radeon AI PRO R9700 next to a 3060AMD Radeon AI PRO R9700 32 GBQwen3-4B-Instruct-2507
Qwen3-4B-Instruct-2507-Q4_K_M.gguf
llama.cpp b11235 (6c7a87f)6478139.6–2026-10-10

Why this site exists

Almost everyone who wants to keep up with AI hits a wall, and it is rarely only the graphics card. The model is a few gigabytes too big. The quant that fits answers worse. The runtime wants a driver you do not have. The tokens per second are fine until the context grows. The power draw, the price of the card, the weeks it takes to learn any of it - all of that decides whether you are in the game or watching it from outside.

The people who get through do it with the same handful of things: a model worth downloading, a box that can hold it, a runtime that works that week, someone who hit the same bug first, a cost they can justify, and an event where the people who built the tools are standing in the same room.

This site keeps track of those things - the models, the hardware and what fits where, the runtimes and their quirks, storage, the tools and what running them actually costs, the people and companies behind them, the books worth reading, the rigs people really built, and where everyone meets next. The list stays short on purpose: an entry is here because it helps someone who does not intend to miss this.

Missing someone? Suggest an entry.