Apple · M1 Pro · Laptop
Best AI Models for MacBook Pro 16" M1 Pro (32 GB)
Runs 9B and 35B MoE models well; 14B and 27–31B fit but are slow (15 and 8 tok/s), and 70B doesn't fit in 28.5 GB.
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 34.8 tok/s | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 39.0 tok/s | |
| 3 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB | 41.2 tok/s | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 42.9 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 48.2 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 34.8 tok/s | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 39.0 tok/s | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 42.9 tok/s | |
| 4 | Q4_K_M · 7.9 GB | 26.4 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 48.2 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 34.8 tok/s | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 39.0 tok/s | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB | 22.0 tok/s | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 42.9 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 48.2 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Q4_K_M · 16.5 GB | 39.0 tok/s | |
| 2 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB | 41.2 tok/s | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB | 22.0 tok/s | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 42.9 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 48.2 tok/s |
| # | Model | Speed ↓ | Score |
|---|---|---|---|
| 1 | GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB | 42.9 tok/s | |
| 2 | Q4_K_M · 19.3 GB | 48.2 tok/s | |
| 3 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB | 41.2 tok/s | |
| 4 | Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB | 41.2 tok/s | |
| 5 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 39.0 tok/s |
The MacBook Pro 16" M1 Pro is a mid-range 32 GB laptop: it runs 9B and 35B MoE models well. Among 32 GB machines, only the M1 Max, M2 Max and Orin write faster. macOS keeps about 3.5 GB, leaving 28.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 19 s before the first word on Qwen3.6 35B A3B. M1 Pro generation, released 2021; the newer M2 Pro writes 0% faster with 1.3× the compute.
MacBook Pro 16" M1 Pro strengths and weaknesses
Strengths
- Runs 35B MoE models: Qwen3.6 35B A3B at 34.8 tok/s in 22 GB
Weaknesses
- 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 28.5 GB usable here
- Slow on large dense models: Qwen3.8 27B at 8.0 tok/s
- Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 2.5 min for the first token
- No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX
Memory for models
28.5 GB of 32 GB70B models need 51.3 GB at Q4, more than the 28.5 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 Qwen3.5 9B.
Output speed depends on memory bandwidth (200 GB/s). Grey rows need more than the 28.5 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB22.0tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB14.7tok/s
- 8.0tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB34.8tok/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
Pro generations: writing vs compute
M1 Pro → M5 ProWriting speed follows memory bandwidth and barely moved: 22.0 to 33.8 tok/s since the M1 Pro. Compute, which sets how fast prompts are read, grew 3.1×. Indexed to the M1 Pro; speeds on Qwen3.5 9B, same 32 GB.
All 1106 models on the MacBook Pro 16" M1 Pro
Featured onlyBest quant that fits in 28.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
OpenCodeReasoning Nemotron 1.1 32BChatCodeReasoning | Q4_K_M | 24.3 GB | 6.8 t/s | 66K | C37, Usable | |
| Q4_K_M | 1.7 GB | 109.4 t/s | 33K | S93, Runs great | ||
| BF16 | 0.2 GB | 608.7 t/s | 1K | S100, Runs great | ||
Qwen3 4B BaseChat | Q4_K_M | 4.2 GB | 48.3 t/s | 33K | A79, Runs well | |
XiYanSQL QwenCoder 32B 2504ChatCode | Q4_K_M | 23.8 GB | 7.0 t/s | 33K | C39, Usable | |
Qwen2.5 0.5BChatFunctions | Q4_K_M | 0.8 GB | 225.8 t/s | 33K | S100, Runs great | |
Qwen3 Next 80B A3B ThinkingChatFunctions | IQ2_M | 27.9 GB | 43.3 t/s | 262K | C44, Usable | |
| Q4_K_M | 7.6 GB | 25.4 t/s | 41K | A66, Runs well | ||
MiniCPM V 2 6Vision | Q4_K_M | 7.9 GB | 26.2 t/s | — | A67, Runs well | |
MythoMax L2 13BChat | Q4_K_M | 11.5 GB | 14.3 t/s | 4K | B54, Decent | |
| BF16 | 1.6 GB | 229.5 t/s | — | S100, Runs great | ||
| Q4_K_M | 6.3 GB | 27.8 t/s | 262K | A68, Runs well | ||
SmolLM2 360MChat | Q4_K_M | 0.8 GB | 233.3 t/s | 8K | S100, Runs great | |
Phi 3.5 Mini InstructChatCode | Q4_K_M | 9.0 GB | 41.2 t/s | 131K | A75, Runs well | |
SmolLM 360MChat | Q4_K_M | 0.6 GB | 233.3 t/s | 2K | S100, Runs great |
Specs
- Chip
- M1 Pro
- CPU cores
- 10
- GPU cores
- 16
- Unified memory
- 32 GB
- For models
- 28.5 GB (macOS keeps 3.5 GB)
- Memory bandwidth
- 200 GB/s
- FP16 (dense)
- 10.4 TFLOPS
- Neural Engine
- 11 TOPS
- Released
- 2021-10-26
MacBook Pro 16" M1 Pro FAQ
How much memory is available for AI on the MacBook Pro 16" M1 Pro (32 GB)?
About 28.5 GB of the 32 GB. macOS keeps roughly 3.5 GB for itself and other apps.
What is the largest model the MacBook Pro 16" M1 Pro (32 GB) can run?
Qwen3.6 35B A3B (36.0B) at Q4_K_M uses 22.0 GB, 77% of the available memory, and runs at about 34.8 tok/s.
Can the MacBook Pro 16" M1 Pro (32 GB) run 70B models?
No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 28.5 GB available.
How long does the MacBook Pro 16" M1 Pro (32 GB) take to read a long prompt?
On Qwen3.6 35B A3B, about 19 s for a 4K-token prompt and 2.5 min for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the MacBook Pro 16" M1 Pro?
An RTX PRO 4500 Blackwell (32 GB) rents from $0.34/hr.