Twoody
Local LLM calculator
The best local LLM for your Mac Studio
From the M1 Max to the M5 Ultra with 512 GB: the largest models a Mac can hold, and how fast they write.
| Your computer | Memory | Strongest that runs comfortably | Writes | Suggested by Twoody by default |
|---|---|---|---|---|
M5 Max — MacBook Pro, Mac Studio |
36 GB | Qwen3.6 35B-A3B One click in Twoody | 100+ tokens/s | Qwen3.5 9B (7.9 GB) |
| 48 GB | Qwen3.6 35B-A3B One click in Twoody | 100+ tokens/s | Qwen3.5 9B (7.9 GB) | |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 98–196 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 128 GB | Qwen3.5 122B-A10B Not in Twoody's catalogue | 36–73 tokens/s | Qwen3.5 9B (7.9 GB) | |
M5 Ultra — Mac Studio |
96 GB | Mistral Small 4 119B Not in Twoody's catalogue | 85–151 tokens/s | Qwen3.5 9B (7.9 GB) |
| 256 GB | Qwen3 235B-A22B Instruct 2507 Not in Twoody's catalogue | 28–50 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 512 GB | Qwen3 235B-A22B Instruct 2507 Not in Twoody's catalogue | 28–50 tokens/s | Qwen3.5 9B (7.9 GB) | |
M3 Ultra — Mac Studio |
96 GB | Mistral Small 4 119B Not in Twoody's catalogue | 59–84 tokens/s | Qwen3.5 9B (7.9 GB) |
| 256 GB | Qwen3 235B-A22B Instruct 2507 Not in Twoody's catalogue | 20–28 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 512 GB | Qwen3 235B-A22B Instruct 2507 Not in Twoody's catalogue | 20–28 tokens/s | Qwen3.5 9B (7.9 GB) | |
M4 Max — MacBook Pro, Mac Studio |
36 GB | Qwen3.6 35B-A3B One click in Twoody | 66–131 tokens/s | Qwen3.5 9B (7.9 GB) |
| 48 GB | Qwen3.6 35B-A3B One click in Twoody | 68–136 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 54–108 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 128 GB | Qwen3.5 122B-A10B Not in Twoody's catalogue | 26–52 tokens/s | Qwen3.5 9B (7.9 GB) | |
M2 Ultra — Mac Studio |
64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 46–92 tokens/s | Qwen3.5 9B (7.9 GB) |
| 128 GB | Qwen3.5 122B-A10B Not in Twoody's catalogue | 28–57 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 192 GB | Qwen3 235B-A22B Instruct 2507 Not in Twoody's catalogue | 20–28 tokens/s | Qwen3.5 9B (7.9 GB) | |
M2 Max — MacBook Pro, Mac Studio |
32 GB | Qwen3.6 35B-A3B One click in Twoody | 50–100 tokens/s | Qwen3.5 9B (7.9 GB) |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 40–79 tokens/s | Qwen3.5 9B (7.9 GB) | |
| 96 GB | Mistral Small 4 119B Not in Twoody's catalogue | 41–59 tokens/s | Qwen3.5 9B (7.9 GB) | |
M1 Ultra — Mac Studio |
64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 36–71 tokens/s | Qwen3.5 9B (7.9 GB) |
| 128 GB | Qwen3.5 122B-A10B Not in Twoody's catalogue | 24–48 tokens/s | Qwen3.5 9B (7.9 GB) | |
M1 Max — MacBook Pro, Mac Studio |
32 GB | Qwen3.6 35B-A3B One click in Twoody | 40–81 tokens/s | Qwen3.5 9B (7.9 GB) |
| 64 GB | Qwen3-Next 80B-A3B Not in Twoody's catalogue | 32–65 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.
How to read this table
One line per chip of this family and per memory size it comes with: the memory decides which models fit, the chip how fast they write.
- 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.
With 128 to 512 GB of unified memory, a Mac Studio holds models no graphics card can: gpt-oss 120B, Qwen3.5 122B-A10B, even Qwen3 235B-A22B.
Its Max and Ultra chips read their memory at 400 GB/s to 1.2 TB/s: mixtures of experts answer at dozens of tokens per second.
Quiet even under load, it keeps its speed through long sessions.
Questions about running an LLM locally
Which LLM for a Mac Studio with an Ultra chip?
With 256 or 512 GB, the strongest model that runs comfortably there is Qwen3 235B-A22B Instruct 2507, which writes 20–50 tokens/s depending on the Mac. It is not in Twoody's catalogue. Twoody suggests Qwen3.5 9B by default, which needs 7.9 GB of memory there: one of the models it has measured with its memory, its tools and your documents.
Is 128 GB enough for a 70B model?
Yes, comfortably: Llama 3.3 70B needs about 45 GB there in Twoody. With 128 GB, the strongest model that runs comfortably there is Qwen3.5 122B-A10B, which writes 24–73 tokens/s depending on the Mac. It is not in Twoody's catalogue. Twoody suggests Qwen3.5 9B by default, which needs 7.9 GB of memory there: one of the models it has measured with its memory, its tools and your documents.
Max or Ultra for a local LLM?
The Ultra doubles the memory bandwidth and the memory: faster answers with large models, and the largest models. For models up to 70B, a Max is enough.
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.