Twoody
Local LLM calculator
The best local LLM for your AMD graphics card
From the RX 7600 to the RX 9070 XT: the strongest model that fits each card's memory, and how fast it writes.
| Your computer | Memory | Strongest that runs comfortably | Writes | Suggested by Twoody by default |
|---|---|---|---|---|
Radeon RX 9070 XT (16 GB) |
16 GB | Qwen3 14B One click in Twoody | 46–67 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 9070 (16 GB) |
16 GB | Qwen3 14B One click in Twoody | 43–62 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 9060 XT (16 GB) |
16 GB | Qwen3 14B One click in Twoody | 23–34 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 9060 XT (8 GB) |
8 GB | Qwen3.5 4B One click in Twoody | 58–117 tokens/s | Qwen3.5 9B (7.9 GB) Partly on the processor: much slower |
Radeon RX 7900 XTX (24 GB) |
24 GB | Qwen3.6 35B-A3B One click in Twoody | 100+ tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 7900 XT (20 GB) |
20 GB | Qwen3.6 35B-A3B One click in Twoody | 96–192 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 7900 GRE (16 GB) |
16 GB | Qwen3 14B One click in Twoody | 41–58 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 7800 XT (16 GB) |
16 GB | Qwen3 14B One click in Twoody | 42–61 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 7600 XT (16 GB) |
16 GB | Qwen3 14B One click in Twoody | 19–28 tokens/s | Qwen3.5 9B (7.9 GB) |
Radeon RX 7600 (8 GB) |
8 GB | Qwen3.5 4B One click in Twoody | 47–95 tokens/s | Qwen3.5 9B (7.9 GB) Partly on the processor: much slower |
Speeds are estimates, not measurements made with Twoody, computed from public llama.cpp benchmarks. Figures reviewed on October 16, 2026.
How to read this table
One line per graphics card: its own memory decides which models fit, and the speeds are those of a model running on the card. The rest of the PC is assumed to have 32 GB of memory.
- Strongest that runs comfortably
- The strongest model that fits comfortably there and writes at least at your reading speed, 5 tokens per second; under its name, whether it installs in one click in Twoody.
- Writes
- Its speed there, in tokens per second: an estimate from public llama.cpp benchmarks, not a measurement made with Twoody.
- Suggested by Twoody by default
- The model the app installs first on that computer, and the memory it needs there. Not always the strongest: one Twoody has measured with its memory, its tools and your documents.
Twoody is in private beta: leave your email to request access.
The card's memory decides which models fit: 16 GB runs models of 14 billion parameters or gpt-oss 20B; the 24 GB RX 7900 XTX, 32 billion.
llama.cpp runs Radeon cards through Vulkan: writing is fast; reading long documents is slower than on NVIDIA cards.
Twoody for Windows and Linux is in private beta: on Windows 10 and 11 (x64), it runs the model on a Radeon card through Vulkan when the driver supports it, and on the processor otherwise; on Linux, on the processor. The speeds on this page are estimates for a model running on the graphics card, not measurements made with Twoody.
Questions about running an LLM locally
Which LLM for a Radeon RX 7900 XTX?
The strongest model that runs comfortably there is Qwen3.6 35B-A3B, which writes 100+ tokens/s. It installs in one click from Twoody's catalogue. On a PC with 32 GB of memory, Twoody suggests Qwen3.5 9B by default, which needs 7.9 GB there: one of the models it has measured with its memory, its tools and your documents.
What fits in 16 GB of VRAM?
The strongest model that runs comfortably there is Qwen3 14B, which writes 19–67 tokens/s depending on the card. It installs in one click from Twoody's catalogue. On a PC with 32 GB of memory, Twoody suggests Qwen3.5 9B by default, which needs 7.9 GB there: one of the models it has measured with its memory, its tools and your documents.
Does Twoody run on Linux with an AMD card?
In the private beta, Twoody runs on Linux (x86_64), but on the processor: it does not use the graphics card there. On Windows 10 and 11 (x64), it uses a Radeon card through Vulkan when the driver supports it. Leave your email on the platforms page to join the waitlist.
The best local LLM, by computer
Try Twoody before it opens to everyone.
The private beta is free, on Mac, Windows and Linux, and on iPhone and Android with Twoody on your computer. Leave your email to ask for an invitation: we will write to you when it is ready for you.