Twoody
Local LLM calculator
Which local LLM can your computer run — and how fast?
Pick your Mac or PC. See which open-weight models fit its memory, how fast they write, how long they take to read a document, and what they are good for.
The models for this computer
On M2 Ultra with 192 GB: 62 of 62 models run well.
What Twoody suggests for this Mac
Qwen3.5 9B, in one click, with conversations of 64k tokens.
Needs 7.9 GB of memory · Runs comfortably · 40–80 tokens/s (feels instant) · 20 pages in 20 s
From 24 GB, Twoody also offers the larger Qwen3.6 35B-A3B: it needs 16.8 GB of memory on this computer.
Twoody is in private beta: leave your email to request access.
Run well on this computer
136.1 of 153.6 GB
Runs comfortably
20–28 tokens/s
near instant
20 pages in 57 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
74.7 of 153.6 GB
Runs comfortably
28–57 tokens/s
near instant
20 pages in 23 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
69.4 of 153.6 GB
Runs comfortably
59–84 tokens/s
feels instant
20 pages in 17 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
46.3 of 153.6 GB
Runs comfortably
46–92 tokens/s
feels instant
20 pages in 7 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
44.9 of 153.6 GB
MLX: 42.3 GB
Runs comfortably
10–15 tokens/s
faster than you read
20 pages in 2 min
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
16.8 of 153.6 GB
Runs comfortably
57–113 tokens/s
feels instant
20 pages in 7 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
21.2 of 153.6 GB
MLX: 20.6 GB
Runs comfortably
53–106 tokens/s
feels instant
20 pages in 7 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
22.9 of 153.6 GB
MLX: 20.6 GB
Runs comfortably
52–104 tokens/s
feels instant
20 pages in 7 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
22.7 of 153.6 GB
MLX: 20.5 GB
Runs comfortably
20–29 tokens/s
near instant
20 pages in 67 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
19.6 of 153.6 GB
MLX: 18.3 GB
Runs comfortably
20–29 tokens/s
near instant
20 pages in 66 s
- Chat and writing
- Your documents
- Translation
- Code
- Agents
21.4 of 153.6 GB
MLX: 17.3 GB
Runs comfortably
40–79 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
19.4 of 153.6 GB
MLX: 18.7 GB
Runs comfortably
22–31 tokens/s
near instant
20 pages in 64 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
19.2 of 153.6 GB
MLX: 17.8 GB
Runs comfortably
63–90 tokens/s
feels instant
20 pages in 9 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
20.5 of 153.6 GB
MLX: 19.4 GB
Runs comfortably
15–30 tokens/s
near instant
20 pages in 58 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
21.4 of 153.6 GB
MLX: 19.4 GB
Runs comfortably
14–29 tokens/s
near instant
20 pages in 58 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
21.5 of 153.6 GB
MLX: 19.4 GB
Runs comfortably
14–28 tokens/s
near instant
20 pages in 58 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
15.5 of 153.6 GB
MLX: 14.9 GB
Runs comfortably
84–121 tokens/s
feels instant
20 pages in 10 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
17.3 of 153.6 GB
MLX: 15.1 GB
Runs comfortably
29–41 tokens/s
near instant
20 pages in 49 s
- Chat and writing
- Your documents
- Translation
- Code
- Agents
11.2 of 153.6 GB
MLX: 10.1 GB
Runs comfortably
40–57 tokens/s
near instant
20 pages in 30 s
- Chat and writing
- Your documents
- Translation
- Reasoning
11.9 of 153.6 GB
MLX: 11.1 GB
Runs comfortably
39–57 tokens/s
near instant
20 pages in 30 s
- Chat and writing
- Your documents
11.6 of 153.6 GB
MLX: 10.6 GB
Runs comfortably
42–60 tokens/s
feels instant
20 pages in 28 s
- Chat and writing
- Your documents
- Translation
7.6 of 153.6 GB
MLX: 6.9 GB
Runs comfortably
43–62 tokens/s
feels instant
20 pages in 24 s
- Chat and writing
- Your documents
- Translation
- Reasoning
7.9 of 153.6 GB
Runs comfortably
51–73 tokens/s
feels instant
20 pages in 21 s
- Chat and writing
- Your documents
- Translation
- Reasoning
7.9 of 153.6 GB
MLX: 7.9 GB
Runs comfortably
40–80 tokens/s
feels instant
20 pages in 20 s
- Chat and writing
- Your documents
- Translation
- Reasoning
6.7 of 153.6 GB
MLX: 5.9 GB
Runs comfortably
51–73 tokens/s
feels instant
20 pages in 19 s
- Chat and writing
- Your documents
- Translation
8.4 of 153.6 GB
MLX: 7.6 GB
Runs comfortably
59–85 tokens/s
feels instant
20 pages in 18 s
- Chat and writing
- Your documents
- Translation
8 of 153.6 GB
MLX: 7.7 GB
Runs comfortably
53–76 tokens/s
feels instant
20 pages in 18 s
- Chat and writing
- Your documents
- Translation
7.2 of 153.6 GB
MLX: 6.8 GB
Runs comfortably
59–85 tokens/s
feels instant
20 pages in 17 s
- Chat and writing
- Your documents
- Translation
- Reasoning
6.9 of 153.6 GB
MLX: 6.5 GB
Runs comfortably
63–90 tokens/s
feels instant
20 pages in 16 s
- Chat and writing
- Your documents
- Translation
8.2 of 153.6 GB
MLX: 7.8 GB
Runs comfortably
63–91 tokens/s
feels instant
20 pages in 15 s
- Chat and writing
- Your documents
6.6 of 153.6 GB
MLX: 5.4 GB
Runs comfortably
71–102 tokens/s
feels instant
20 pages in 9 s
- Chat and writing
- Translation
4.9 of 153.6 GB
MLX: 5.2 GB
Runs comfortably
58–117 tokens/s
feels instant
20 pages in 10 s
- Chat and writing
- Translation
4.9 of 153.6 GB
MLX: 4.7 GB
Runs comfortably
81–116 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
- Translation
3.6 of 153.6 GB
MLX: 3.5 GB
Runs comfortably
49–99 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
5 of 153.6 GB
MLX: 4.5 GB
Runs comfortably
100+ tokens/s
feels instant
20 pages in 8 s
- Chat and writing
- Translation
4.6 of 153.6 GB
MLX: 4.3 GB
Runs comfortably
87–125 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
- Translation
3.9 of 153.6 GB
MLX: 3.7 GB
Runs comfortably
100+ tokens/s
feels instant
20 pages in 6 s
- Chat and writing
- Translation
4.7 of 153.6 GB
MLX: 3.7 GB
Runs comfortably
99–142 tokens/s
feels instant
20 pages in 5 s
2.9 of 153.6 GB
MLX: 2.7 GB
Runs comfortably
91–182 tokens/s
feels instant
20 pages in 5 s
1.7 of 153.6 GB
MLX: 1.6 GB
Runs comfortably
87–262 tokens/s
feels instant
20 pages in 2 s
59.9 of 153.6 GB
Runs comfortably
63–90 tokens/s
feels instant
20 pages in 13 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
22.8 of 153.6 GB
MLX: 21.5 GB
Runs comfortably
20–29 tokens/s
near instant
20 pages in 67 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
18.1 of 153.6 GB
MLX: 16.8 GB
Runs comfortably
66–95 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
19.1 of 153.6 GB
MLX: 17.8 GB
Runs comfortably
63–90 tokens/s
feels instant
20 pages in 9 s
- Chat and writing
- Your documents
- Translation
- Code
- Agents
19.2 of 153.6 GB
MLX: 17.8 GB
Runs comfortably
63–90 tokens/s
feels instant
20 pages in 9 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
16.1 of 153.6 GB
Runs comfortably
29–41 tokens/s
near instant
20 pages in 49 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
16.1 of 153.6 GB
MLX: 16.9 GB
Runs comfortably
29–41 tokens/s
near instant
20 pages in 49 s
- Chat and writing
- Your documents
- Translation
- Code
- Agents
12 of 153.6 GB
MLX: 11.9 GB
Runs comfortably
89–128 tokens/s
feels instant
20 pages in 9 s
- Chat and writing
- Your documents
- Translation
- Code
- Reasoning
- Agents
10.4 of 153.6 GB
MLX: 9 GB
Runs comfortably
100+ tokens/s
feels instant
20 pages in 6 s
- Chat and writing
- Your documents
- Translation
- Code
11.7 of 153.6 GB
MLX: 11 GB
Runs comfortably
37–53 tokens/s
near instant
20 pages in 30 s
- Chat and writing
- Your documents
- Translation
- Reasoning
11.9 of 153.6 GB
MLX: 12 GB
Runs comfortably
39–57 tokens/s
near instant
20 pages in 30 s
- Chat and writing
- Your documents
- Reasoning
10.5 of 153.6 GB
MLX: 10.6 GB
Runs comfortably
42–60 tokens/s
feels instant
20 pages in 28 s
- Chat and writing
- Your documents
- Translation
- Reasoning
6.7 of 153.6 GB
MLX: 5.9 GB
Runs comfortably
51–73 tokens/s
feels instant
20 pages in 19 s
- Chat and writing
- Your documents
- Translation
- Reasoning
7.2 of 153.6 GB
MLX: 6.8 GB
Runs comfortably
59–85 tokens/s
feels instant
20 pages in 17 s
- Chat and writing
- Your documents
- Translation
- Reasoning
6.9 of 153.6 GB
MLX: 6.5 GB
Runs comfortably
63–90 tokens/s
feels instant
20 pages in 16 s
- Chat and writing
- Your documents
- Translation
- Reasoning
5.5 of 153.6 GB
MLX: 5.2 GB
Runs comfortably
69–99 tokens/s
feels instant
20 pages in 15 s
- Chat and writing
- Your documents
- Translation
- Reasoning
4.9 of 153.6 GB
MLX: 4.7 GB
Runs comfortably
81–116 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
- Translation
4.6 of 153.6 GB
MLX: 4.3 GB
Runs comfortably
87–125 tokens/s
feels instant
20 pages in 8 s
- Chat and writing
3.2 of 153.6 GB
MLX: 3 GB
Runs comfortably
90–129 tokens/s
feels instant
20 pages in 6 s
- Chat and writing
- Translation
2.4 of 153.6 GB
MLX: 2.7 GB
Runs comfortably
74–148 tokens/s
feels instant
20 pages in 6 s
2.5 of 153.6 GB
Runs comfortably
85–122 tokens/s
feels instant
20 pages in 5 s
1.6 of 153.6 GB
MLX: 1.4 GB
Runs comfortably
100+ tokens/s
feels instant
20 pages in 2 s
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. Speeds are estimates, not measurements made with Twoody, computed from public llama.cpp benchmarks. Figures reviewed on October 16, 2026.
How to read the results
Choose your computer and its memory. The calculator goes through the models of Twoody's catalogue, and a few larger ones it does not offer, and tells how each one would run on that computer.
- What Twoody suggests
- The model the app installs first on that computer, one it has measured with its memory, its tools and your documents, and the memory it needs there.
- Run well on this computer
- The models that fit its memory, the strongest first: “Runs comfortably”, or “Runs — close other apps” when little room is left. Further down, the models that would run partly on the processor, much slower, then those that are too big.
- Memory
- What Twoody shows in “Models” for that computer: the model's files, the conversation it keeps in mind and room to work. The bar shows how much it takes of the memory a model may use there.
- Writes
- How fast the model writes its answer, in tokens per second. A token is a piece of a word, and you read silently at about 5 tokens per second.
- Reads a document
- How long the model takes to read a document of about 20 pages before it answers about it.
- Good for
- What its size suits: chat and writing, your documents, translation, code, reasoning or agents.
- One click in Twoody
- The model is in Twoody's catalogue and installs from the app in one click; the others say “Not in Twoody's catalogue”.
How much memory do you need for a local LLM?
Memory decides which models fit: the model's file and the one that lets it read images, the conversation it keeps in mind (8k to 64k tokens depending on the computer's memory, as in Twoody), and a little room to work. A Mac lets its graphics use about two thirds of its memory up to 32 GB, three quarters above. What runs comfortably:
| Memory | Strongest that run comfortably | Suggested by Twoody by default |
|---|---|---|
| 8 GB | Qwen3.5 4B, Qwen3 4B Instruct 2507, Nemotron 3 Nano 4B | Qwen3.5 4B (4 GB) |
| 16 GB | Gemma 4 12B, GLM-4.6V Flash, Qwen3.5 9B | Qwen3.5 9B (7.4 GB) |
| 24 GB | Qwen3 14B, Phi-4 14B, Ministral 3 14B | Qwen3.5 9B (7.4 GB) |
| 32 GB | Qwen3.6 35B-A3B, Gemma 4 31B, Qwen3 30B-A3B Instruct 2507 | Qwen3.5 9B (7.9 GB) |
| 48 GB | Qwen3.6 35B-A3B, Qwen3.6 35B-A3B (4 bits), Qwen3.5 35B-A3B | Qwen3.5 9B (7.9 GB) |
| 64 GB | Qwen3-Next 80B-A3B*, Llama 3.3 70B, Qwen3.6 35B-A3B | Qwen3.5 9B (7.9 GB) |
| 128 GB | Qwen3.5 122B-A10B*, Mistral Small 4 119B*, Qwen3-Next 80B-A3B* | Qwen3.5 9B (7.9 GB) |
| 256 GB | Qwen3 235B-A22B Instruct 2507*, Qwen3.5 122B-A10B*, Mistral Small 4 119B* | Qwen3.5 9B (7.9 GB) |
| 512 GB | Qwen3 235B-A22B Instruct 2507*, Qwen3.5 122B-A10B*, Mistral Small 4 119B* | Qwen3.5 9B (7.9 GB) |
* Not in Twoody's catalogue; the others install in one click.
Why memory bandwidth sets the speed
To write each word, the computer reads the model's active weights from memory. Speed therefore follows memory bandwidth more than processor power. Qwen3 8B, 4-bit, on a few machines:
| Computer | Memory bandwidth | Writes |
|---|---|---|
| M1 | 68 GB/s | 8.7–12 tokens/s |
| M2 | 100 GB/s | 13–19 tokens/s |
| M4 | 120 GB/s | 15–21 tokens/s |
| M5 | 153 GB/s | 19–27 tokens/s |
| M4 Pro | 273 GB/s | 31–45 tokens/s |
| M4 Max | 546 GB/s | 53–76 tokens/s |
| M5 Max | 614 GB/s | 72–104 tokens/s |
| GeForce RTX 4090 (24 GB) | 1,008 GB/s | 100+ tokens/s |
4-bit or 8-bit?
Models are shared compressed. 4-bit files (Q4_K_M, Q4_0 for Gemma, MXFP4 for gpt-oss) are half the size of 8-bit ones for a small loss in quality: it is what Twoody installs (3-bit for the larger Qwen3.6 35B-A3B, so that it fits a 24 GB Mac) and what this calculator counts. 8-bit is a little finer and needs twice the memory.
Tokens per second: what it feels like
A token is about three quarters of a word. You read silently at 5 to 6 tokens per second.
| under 5 | slower than you read |
| 5 to 10 | about your reading speed |
| 10 to 20 | faster than you read |
| 20 to 50 | near instant |
| over 50 | feels instant |
A model that thinks first writes 300 to 3,000 tokens of reasoning before its answer: at 10 tokens per second, from half a minute to five minutes. In Twoody, the Fast, Thinking and Deep settings choose how long it thinks.
Reading a document
Before answering about a document, the model reads it — and that is where recent chips gain the most. Qwen3 8B reading a 20-page document, with 16 GB:
| M1 | 3 min |
| M4 | 76 s |
| M5 | 27 s |
Mac or PC?
A Mac shares its memory between the processor and the graphics: a 64 GB Mac runs models no 24 GB graphics card holds. A PC graphics card has less memory but reads it very fast: with a model that fits, an RTX 4090 writes faster than any Mac. Twoody is in private beta on Mac, Windows and Linux: on Windows, it uses the graphics card through Vulkan when the driver supports it; on Linux, it runs the model on the processor.
The best local LLM, by computer
Method and sources
The memory is not this site's estimate: it is the Twoody app's own calculation, with the same files and the same conversation length — the model's file, the file it reads images with and 0.3 GB to use it, the conversation (in q8_0, 8 bits, for a hybrid model such as Qwen3.5; in 16 bits otherwise), the state of its recurrent layers and 0.3 GB of working memory. Measured with llama.cpp, Qwen3.5 9B with a conversation of 32k tokens takes 7.4 GB, as computed. The models are those of Twoody's catalogue, checked on Hugging Face on October 15, 2026, and a few larger ones it does not offer, counted the same way.
Each machine's speed is computed from its measured speed on llama.cpp's reference model (LLaMA 2 7B, 4-bit), scaled by what each model reads per word, with the memory bandwidths of Apple's and NVIDIA's specifications. Checked against 20 published measurements that were not used to build it: median error 4.5 %, largest 23 %, all within the ranges shown.
Figures reviewed on October 16, 2026.
Sources
- www.apple.com/newsroom/
- support.apple.com/specs
- github.com/ggml-org/llama.cpp/discussions/4167
- github.com/ggml-org/llama.cpp/discussions/15013
- github.com/ggml-org/llama.cpp/discussions/10879
- github.com/ggml-org/llama.cpp/discussions/15396
- www.nvidia.com/en-us/geforce/graphics-cards/compare/
- huggingface.co/models
- www.sciencedirect.com/science/article/abs/pii/S0749596X19300786
Questions about running an LLM locally
Can I run a local LLM with 8 GB of memory?
Yes, a small one. On a Mac with Apple silicon and 8 GB, the strongest models that run comfortably are Qwen3.5 4B, Qwen3 4B Instruct 2507 and Nemotron 3 Nano 4B. All install in one click from Twoody's catalogue. Twoody suggests Qwen3.5 4B by default, which needs 4 GB of memory there: one of the models it has measured with its memory, its tools and your documents. Close heavy apps while you use it.
Which LLM for a Mac with 16 GB?
On a Mac with Apple silicon and 16 GB, the strongest models that run comfortably are Gemma 4 12B, GLM-4.6V Flash and Qwen3.5 9B. All install in one click from Twoody's catalogue. Twoody suggests Qwen3.5 9B by default, which needs 7.4 GB of memory there: one of the models it has measured with its memory, its tools and your documents.
How much memory does a 70B model need?
About 45 GB in Twoody, with a conversation of 16k tokens: a Mac with 64 GB runs Llama 3.3 70B, at 4.2–15 tokens/s depending on the chip. Mixtures of experts such as gpt-oss 120B need more memory (60 GB) but write much faster.
Is a 4-bit model much worse than an 8-bit one?
Slightly. For writing, summaries and questions about documents the difference is hard to notice, and 4-bit halves the memory and doubles the speed: it is what Twoody installs, and what this calculator counts.
Mac or NVIDIA graphics card for a local LLM?
A graphics card writes faster with a model that fits its memory (8 to 32 GB); a Mac holds much larger models in its unified memory (up to 512 GB). For one person working on documents, a Mac with 16 to 64 GB is the simplest choice.
Does a local LLM make a MacBook Air too hot?
A MacBook Air has no fan: after a few minutes of continuous writing it slows down to stay cool. For answers of normal length it is not noticeable; for long sessions, a MacBook Pro or a Mac mini keeps its speed.
Do I need to install anything besides Twoody?
No: Twoody downloads the model and runs it with its own engine, llama.cpp, in one click. On a Mac with Apple silicon, it can also install MLX, Apple's engine, if you ask it to (Models › “Advanced”).
How accurate are these figures?
The memory is what the Twoody app shows, computed the same way: for Qwen3.5 9B with a conversation of 32k tokens, llama.cpp measured 7.4 GB, as computed. The speeds are estimates: on 20 published measurements that were not used to build the formula, the median error is 4.5 % and the largest 23 %; each fell within the range shown. Your speed also depends on the app, its version and what else the computer is doing.
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.