Apple · M2 · Laptop
Best AI Models for MacBook Pro 13" M2 (24 GB)
Runs 27–31B models at 4 tok/s; 9B and 14B fit but are slow (11 and 7 tok/s), and 70B doesn't fit in 20.5 GB.
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB | 22.1 tok/s | |
| 2 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB | 11.0 tok/s | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 23.9 tok/s | |
| 4 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB | 24.6 tok/s | |
| 5 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB | 21.5 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB | 22.1 tok/s | |
| 2 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 23.9 tok/s | |
| 3 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB | 24.6 tok/s | overall |
| 4 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB | 21.5 tok/s | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB | 55.1 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB | 23.9 tok/s | |
| 2 | Q4_K_M · 2.3 GB | 85.4 tok/s | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 22.1 tok/s | |
| 4 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB | 21.5 tok/s | |
| 5 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB | 55.1 tok/s |
| # | Model | Speed ↓ | Score |
|---|---|---|---|
| 1 | GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB | 23.9 tok/s | |
| 2 | Ling 3.0 TinyInclusion AI Q4_K_M · 5.5 GB | 55.1 tok/s | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 22.1 tok/s | |
| 4 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB | 21.5 tok/s | |
| 5 | Gemma 4 E2B ITGoogle Q4_K_M · 3.5 GB | 20.4 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB | 22.1 tok/s | |
| 2 | Gemma 3 4B ITGoogle Q4_K_M · 5.0 GB | 24.6 tok/s | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB | 11.0 tok/s | |
| 4 | Qwen3.5 4BAlibaba Q4_K_M · 3.4 GB | 21.5 tok/s | |
| 5 | Cosmos Reason2 2BNVIDIA Q4_K_M · 3.5 GB | 43.5 tok/s |
The MacBook Pro 13" M2 is a 24 GB laptop with more memory than speed: it runs 27–31B models at 4 tok/s. macOS keeps about 3.5 GB, leaving 20.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 25 s before the first word on Gemma 4 26B A4B IT. M2 generation, released 2022; the newer M3 writes 2% faster with 1.0× the compute.
MacBook Pro 13" M2 strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 22.1 tok/s in 19.8 GB
Weaknesses
- 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 20.5 GB usable here
- Slow on large dense models: Qwen3.8 27B at 4.0 tok/s
- Slow prompt reading: A 32K-token prompt on Gemma 4 26B A4B IT waits 3.4 min for the first token
- No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX
Memory for models
20.5 GB of 24 GB70B models need 51.3 GB at Q4, more than the 20.5 GB available.
Other memory sizes of the same machine first, then machines and GPUs people weigh against it, each with the one reason it is worth a look. Speeds on Qwen3.6 35B A3B.
Output speed depends on memory bandwidth (100 GB/s). Grey rows need more than the 20.5 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB11.0tok/s
- 7.4tok/s
- 4.0tok/s
- 22.1tok/s
- 70BLlama 3.3 70B Instruct · does not fitneeds 51.3 GB
- 120B MoEGPT OSS 120B · does not fitneeds 70.8 GB
Estimated speeds: Q4_K_M, 4K context, one user. How we estimate
Chip generations: writing vs compute
M1 → M5Writing speed follows memory bandwidth and barely moved: 24.9 to 31.1 tok/s since the M1. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1; speeds on Qwen3.6 35B A3B, same 16 GB.
All 1068 models on the MacBook Pro 13" M2
Featured onlyBest quant that fits in 20.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
QwQ 32B PreviewChatReasoning | IQ3_M | 19.3 GB | 4.5 t/s | 33K | D20, Barely runs | |
C4ai Command R V01ChatFunctions | IQ3_S | 20.2 GB | 4.3 t/s | — | F11, Won't fit | |
Qwen1.5 32BChat | Q3_K_M | 20.4 GB | 4.2 t/s | 33K | F9, Won't fit | |
Aya 23 8BChat | BF16 | 20.2 GB | 4.0 t/s | — | F10, Won't fit | |
Deepseek Coder 1.3B BaseChatCode | Q4_K_M | 4.3 GB | 47.3 t/s | 16K | A79, Runs well | |
| IQ2_M | 18.9 GB | 4.7 t/s | — | D23, Barely runs | ||
Qwen1.5 32B ChatChat | Q3_K_M | 20.4 GB | 4.2 t/s | 33K | F9, Won't fit | |
Deepseek Coder 6.7B BaseChatCode | Q4_K_M | 12.9 GB | 12.9 t/s | 16K | B52, Decent | |
OpenCodeReasoning Nemotron 1.1 32BChatCodeReasoning | Q2_K | 18.5 GB | 4.7 t/s | 66K | D27, Barely runs | |
Deepseek Coder 33B BaseChatCode | IQ3_M | 19.5 GB | 4.4 t/s | 16K | D18, Barely runs | |
| IQ2_M | 18.2 GB | 14.1 t/s | 33K | C41, Usable | ||
Qwen2.5 32BChat | Q2_K | 18.5 GB | 4.7 t/s | 131K | D27, Barely runs | |
OpenReasoning Nemotron 32BChatCodeReasoning | Q2_K | 18.5 GB | 4.7 t/s | 131K | D27, Barely runs | |
| BF16 | 20.2 GB | 4.0 t/s | — | F10, Won't fit | ||
Falcon 40BChat | IQ2_M | 19.6 GB | 4.5 t/s | — | D16, Barely runs |
Specs
- Chip
- M2
- CPU cores
- 8
- GPU cores
- 10
- Unified memory
- 24 GB
- For models
- 20.5 GB (macOS keeps 3.5 GB)
- Memory bandwidth
- 100 GB/s
- FP16 (dense)
- 7.2 TFLOPS
- Neural Engine
- 16 TOPS
- Released
- 2022-06-24
MacBook Pro 13" M2 FAQ
How much memory is available for AI on the MacBook Pro 13" M2 (24 GB)?
About 20.5 GB of the 24 GB. macOS keeps roughly 3.5 GB for itself and other apps.
What is the largest model the MacBook Pro 13" M2 (24 GB) can run?
Qwen3.6 35B A3B (36.0B) at IQ4_XS uses 19.8 GB, 97% of the available memory, and runs at about 22.1 tok/s.
Can the MacBook Pro 13" M2 (24 GB) run Gemma 4 26B A4B IT?
Yes. Gemma 4 26B A4B IT fits at Q4_K_M, using 16.5 GB of the 20.5 GB available, and it is the best model that runs well on this machine.
Can the MacBook Pro 13" M2 (24 GB) run 70B models?
No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 20.5 GB available.
How long does the MacBook Pro 13" M2 (24 GB) take to read a long prompt?
On Gemma 4 26B A4B IT, about 25 s for a 4K-token prompt and 3.4 min for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the MacBook Pro 13" M2?
An RTX 3090 (24 GB) rents from $0.17/hr.