Twoody
Local LLM calculator
A local LLM on the RTX 5070
With 12 GB of its own memory: which open-weight models fit the RTX 5070, how fast they write and read, and how it compares with RTX 5070 Ti, RTX 4070, RTX 5060 Ti (16 GB) and Radeon RX 9070. Computed with the memory Twoody's app shows and public llama.cpp benchmarks.
The best local LLM for the RTX 5070
| Memory | Strongest that runs comfortably | Writes | Suggested by Twoody by default |
|---|---|---|---|
| 12 GB | Gemma 4 12B One click in Twoody | 56–81 tokens/s | Qwen3.5 9B (7.9 GB) |
Speeds are estimates, not measurements made with Twoody, computed from public llama.cpp benchmarks. Figures reviewed on October 16, 2026.
“Strongest that runs comfortably”: the strongest model that fits comfortably in the card's memory and writes at least at your reading speed (5 tokens per second). “Suggested by Twoody by default”: the model the app installs first on a PC with this card and 32 GB of memory, and the memory it needs there.
Twoody is in private beta: leave your email to request access.
Every model that runs well on the RTX 5070
33 of the 62 models the calculator knows (Twoody's catalogue and a few larger ones) run well here, the strongest first: the memory Twoody's app says each one needs on this computer, how fast it writes, and how long it takes to read a document.
| Model | Memory | Writes | Reads a document |
|---|---|---|---|
| Qwen3 14B One click in Twoody | Needs 11.2 GB of memory Runs — close other apps | 46–66 tokens/s | 20 pages in 6 s |
| Ministral 3 14B One click in Twoody | Needs 11.6 GB of memory Runs — close other apps | 50–71 tokens/s | 20 pages in 6 s |
| Gemma 4 12B One click in Twoody | Needs 7.6 GB of memory Runs comfortably | 56–81 tokens/s | 20 pages in 5 s |
| GLM-4.6V Flash One click in Twoody | Needs 7.9 GB of memory Runs comfortably | 65–94 tokens/s | 20 pages in 4 s |
| Qwen3.5 9B One click in Twoody | Needs 7.9 GB of memory Runs comfortably | 55–110 tokens/s | 20 pages in 4 s |
| GLM-4 9B One click in Twoody | Needs 6.7 GB of memory Runs comfortably | 65–94 tokens/s | 20 pages in 4 s |
| Ministral 3 8B One click in Twoody | Needs 8.4 GB of memory Runs comfortably | 76–109 tokens/s | 20 pages in 4 s |
| Granite 4.1 8B One click in Twoody | Needs 8 GB of memory Runs comfortably | 70–101 tokens/s | 20 pages in 4 s |
| Qwen3 8B One click in Twoody | Needs 7.2 GB of memory Runs comfortably | 78–112 tokens/s | 20 pages in 3 s |
| Llama 3.1 8B One click in Twoody | Needs 6.9 GB of memory Runs comfortably | 80–116 tokens/s | 20 pages in 3 s |
| Olmo 3 7B One click in Twoody | Needs 8.2 GB of memory Runs comfortably | 81–117 tokens/s | 20 pages in 3 s |
| Gemma 4 E4B One click in Twoody | Needs 6.6 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Qwen3.5 4B One click in Twoody | Needs 4.9 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Qwen3 4B Instruct 2507 One click in Twoody | Needs 4.9 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Nemotron 3 Nano 4B One click in Twoody | Needs 3.6 GB of memory Runs comfortably | 96–192 tokens/s | 20 pages in 2 s |
| Ministral 3 3B One click in Twoody | Needs 5 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Phi-4 mini One click in Twoody | Needs 4.6 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Llama 3.2 3B One click in Twoody | Needs 3.9 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| Gemma 4 E2B One click in Twoody | Needs 4.7 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| Qwen3.5 2B One click in Twoody | Needs 2.9 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| Qwen3.5 0.8B One click in Twoody | Needs 1.7 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| DeepSeek-Coder-V2 Lite One click in Twoody | Needs 10.4 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Ministral 3 14B Reasoning One click in Twoody | Needs 10.5 GB of memory Runs comfortably | 50–71 tokens/s | 20 pages in 6 s |
| GLM-Z1 9B One click in Twoody | Needs 6.7 GB of memory Runs comfortably | 65–94 tokens/s | 20 pages in 4 s |
| DeepSeek-R1 8B One click in Twoody | Needs 7.2 GB of memory Runs comfortably | 78–112 tokens/s | 20 pages in 3 s |
| DeepSeek-R1 Distill Llama 8B One click in Twoody | Needs 6.9 GB of memory Runs comfortably | 80–116 tokens/s | 20 pages in 3 s |
| DeepSeek-R1 Distill Qwen 7B One click in Twoody | Needs 5.5 GB of memory Runs comfortably | 86–124 tokens/s | 20 pages in 3 s |
| Qwen3 4B Thinking 2507 One click in Twoody | Needs 4.9 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| Phi-4 mini reasoning One click in Twoody | Needs 4.6 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 2 s |
| SmolLM3 3B One click in Twoody | Needs 3.2 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| LFM2.5 2.6B One click in Twoody | Needs 2.4 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| MiniCPM5 2B One click in Twoody | Needs 2.5 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
| Llama 3.2 1B One click in Twoody | Needs 1.6 GB of memory Runs comfortably | 100+ tokens/s | 20 pages in 1 s |
Besides these, 23 models would run partly on the processor, much slower, and 6 are too big for this computer. See them all in the calculator.
Each model's memory is what Twoody shows in “Models” for this computer: the same formula, the same files (the one for reading images included), the same conversation length — catalogue checked on October 15, 2026.
RTX 5070 compared with RTX 5070 Ti, RTX 4070, RTX 5060 Ti (16 GB) and Radeon RX 9070
| Computer | Memory | Qwen3.5 9B writes | Reads a document | Strongest that runs comfortably |
|---|---|---|---|---|
| RTX 5070 | 12 GB | 55–110 tokens/s | 20 pages in 4 s | Gemma 4 12B 56–81 tokens/s |
| RTX 5070 Ti | 16 GB | 76–153 tokens/s | 20 pages in 3 s | Qwen3 14B 63–91 tokens/s |
| RTX 4070 | 12 GB | 40–80 tokens/s | 20 pages in 7 s | Gemma 4 12B 41–59 tokens/s |
| RTX 5060 Ti (16 GB) | 16 GB | 39–78 tokens/s | 20 pages in 6 s | Qwen3 14B 32–46 tokens/s |
| Radeon RX 9070 | 16 GB | 52–103 tokens/s | 20 pages in 7 s | Qwen3 14B 43–62 tokens/s |
The card's own memory decides which models fit; its bandwidth, how fast they write. Each PC is assumed to have 32 GB of memory beside its card.
This card has 12 GB of memory of its own (VRAM), read at 672 GB/s: a model that fits it entirely writes fast; a larger one spills into the computer's memory and slows down a lot.
The tables assume 32 GB of memory in the PC beside the card. The speeds are those of a model running on the card, estimated from public llama.cpp benchmarks.
Twoody for Windows and Linux is in private beta: on Windows 10 and 11 (x64), it runs the model on the RTX 5070 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 card, not measurements made with Twoody.
Questions about running an LLM locally
Which local LLM for the RTX 5070?
The strongest model that runs comfortably there is Gemma 4 12B, which writes 56–81 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 the RTX 5070's 12 GB?
33 of the 62 models the calculator knows (Twoody's catalogue and a few larger ones) run well there, on the card; the largest is Ministral 3 14B, which needs 11.6 GB. Larger ones spill into the computer's memory and slow down a lot.
How many tokens per second does the RTX 5070 write?
With Qwen3.5 9B, the model Twoody suggests there, it writes 55–110 tokens/s and reads a document of about 20 pages in 4 s. These speeds are estimates from public llama.cpp benchmarks, for a model running on the card, not measurements made with Twoody.
How does the RTX 5070 compare with the RTX 5070 Ti, RTX 4070, RTX 5060 Ti (16 GB) and Radeon RX 9070?
With Qwen3.5 9B, the model Twoody suggests: RTX 5070, 55–110 tokens/s; RTX 5070 Ti, 76–153 tokens/s; RTX 4070, 40–80 tokens/s; RTX 5060 Ti (16 GB), 39–78 tokens/s; Radeon RX 9070, 52–103 tokens/s. The card's memory decides which models fit; its bandwidth, how fast they write.
Does Twoody use the RTX 5070?
In the private beta, on Windows 10 and 11 (x64), yes: Twoody runs the model on the card through Vulkan when the driver supports it, and on the processor otherwise. On Linux, it runs the model on the processor. Leave your email to join the waitlist.
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.