Apple · M5 Pro · Laptop
Best AI Models for MacBook Pro 16" M5 Pro (64 GB)
Runs 14B and 35B MoE models well and fits 120B MoE; 27–31B and 70B fit but are slow (12 and 5 tok/s).
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 46.5 tok/s | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 53.2 tok/s | |
| 3 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB | 52.2 tok/s | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 59.3 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 58.4 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 46.5 tok/s | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 53.2 tok/s | |
| 3 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 59.3 tok/s | |
| 4 | Q4_K_M · 7.9 GB | 40.5 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 58.4 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 46.5 tok/s | |
| 2 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 53.2 tok/s | |
| 3 | Qwen3.5 9BAlibaba Q4_K_M · 6.6 GB | 33.8 tok/s | |
| 4 | GPT OSS 20BOpenAI Q4_K_M · 13.1 GB | 59.3 tok/s | |
| 5 | Q4_K_M · 19.3 GB | 58.4 tok/s |
| # | Model | Speed | Score |
|---|---|---|---|
| 1 | Qwen3.6 35B A3BAlibabaHow to run → Q4_K_M · 22.0 GB | 46.5 tok/s | |
| 2 | Qwen3.8 27BAlibaba Q4_K_M · 17.9 GB | 12.3 tok/s | |
| 3 | Qwen3.6 27BAlibaba Q4_K_M · 17.9 GB | 12.3 tok/s | |
| 4 | Q4_K_M · 19.3 GB | 58.4 tok/s | |
| 5 | GLM 4.7 FlashZ.ai Q4_K_M · 19.9 GB | 43.5 tok/s |
| # | Model | Speed ↓ | Score |
|---|---|---|---|
| 1 | GPT OSS 20BOpenAIHow to run → Q4_K_M · 13.1 GB | 59.3 tok/s | |
| 2 | Q4_K_M · 19.3 GB | 58.4 tok/s | |
| 3 | Gemma 4 26B A4B ITGoogle Q4_K_M · 16.5 GB | 53.2 tok/s | |
| 4 | Qwen3 30B A3B Thinking 2507Alibaba Q4_K_M · 19.4 GB | 52.2 tok/s | |
| 5 | Qwen3 30B A3B Instruct 2507Alibaba Q4_K_M · 19.4 GB | 52.2 tok/s |
The MacBook Pro 16" M5 Pro is a 64 GB laptop with more memory than speed: it runs 14B and 35B MoE models well and fits 120B MoE. macOS keeps about 3.5 GB, leaving 60.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 6.0 s before the first word on Qwen3.6 35B A3B. M5 Pro generation, released 2026.
MacBook Pro 16" M5 Pro strengths and weaknesses
Strengths
- Runs 120B MoE models: GPT OSS 120B at 48.4 tok/s in 59.1 GB
Weaknesses
- Slow on large dense models: Llama 3.3 70B Instruct at 4.6 tok/s, Qwen3.8 27B at 12.3 tok/s
- Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 48.0 s for the first token
- No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX
Memory for models
60.5 GB of 64 GBEverything on the size ladder fits. Qwen3.6 35B A3B and Gemma 4 26B A4B IT together use 38.5 GB and leave 22 GB free.
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 (307 GB/s). Grey rows need more than the 60.5 GB available.
- 9BQwen3.5 9B · Q4_K_M · 6.6 GB33.8tok/s
- 14BQwen3 14B · Q4_K_M · 11.9 GB22.6tok/s
- 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB12.3tok/s
- 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB46.5tok/s
- 4.6tok/s
- 48.4tok/s
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 1168 models on the MacBook Pro 16" M5 Pro
Featured onlyBest quant that fits in 60.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works
| Model | Quant | VRAM | Speed | Context | Score | Fit |
|---|---|---|---|---|---|---|
Granite Docling 258MVisionChatCodeMath | Q4_K_M | 0.6 GB | 429.8 t/s | 8K | S100, Runs great | |
| Q4_K_M | 7.3 GB | 39.9 t/s | 131K | A75, Runs well | ||
| BF16 | 4.3 GB | 78.7 t/s | — | S87, Runs great | ||
| Q4_K_M | 17.9 GB | 12.3 t/s | 262K | B51, Decent | ||
Phi 4 Mini Flash ReasoningChatMathCodeReasoning | Q4_K_M | 5.3 GB | 72.8 t/s | 262K | S86, Runs great | |
Qwen2.5 VL 72B InstructVision | Q4_K_M | 49.7 GB | 4.8 t/s | 128K | C39, Usable | |
Rnj 1.5 InstructChat | BF16 | 19.1 GB | 12.5 t/s | 164K | B51, Decent | |
Qwen3.8 Flash NextVisionFunctions | IQ2_S | 57.2 GB | 10.0 t/s | 262K | D25, Barely runs | |
| Q4_K_M | 4.2 GB | 74.1 t/s | 33K | S86, Runs great | ||
| Q4_K_M | 1.0 GB | 302.7 t/s | 8K | S100, Runs great | ||
| Q4_K_M | 7.6 GB | 38.9 t/s | 41K | A75, Runs well | ||
SmolLM3 3B ONNXChat | Q4_K_M | 3.3 GB | 95.5 t/s | 66K | S90, Runs great | |
Athene v2 ChatChatFunctions | Q4_K_M | 49.3 GB | 4.8 t/s | 33K | C40, Usable | |
PowerMoE 3BChat | Q4_K_M | 2.6 GB | 103.6 t/s | 4K | S92, Runs great | |
Gemma4 E4B MiniFantasy V1ChatRoleplay | BF16 | 16.8 GB | 13.0 t/s | 131K | B52, Decent |
Specs
- Chip
- M5 Pro
- CPU cores
- 18
- GPU cores
- 20
- Unified memory
- 64 GB
- For models
- 60.5 GB (macOS keeps 3.5 GB)
- Memory bandwidth
- 307 GB/s
- FP16 (dense)
- 32.3 TFLOPS
- Neural Engine
- 38 TOPS
- Released
- 2026-03-11
MacBook Pro 16" M5 Pro FAQ
How much memory is available for AI on the MacBook Pro 16" M5 Pro (64 GB)?
About 60.5 GB of the 64 GB. macOS keeps roughly 3.5 GB for itself and other apps.
What is the largest model the MacBook Pro 16" M5 Pro (64 GB) can run?
GPT OSS 120B (116.8B) at Q4_0 uses 59.1 GB, 98% of the available memory, and runs at about 48.4 tok/s.
Can the MacBook Pro 16" M5 Pro (64 GB) run 70B models?
Yes, but slowly: Llama 3.3 70B Instruct at Q4_K_M uses 51.3 GB and writes about 4.6 tok/s.
How long does the MacBook Pro 16" M5 Pro (64 GB) take to read a long prompt?
On Qwen3.6 35B A3B, about 6.0 s for a 4K-token prompt and 48 s for a 32K-token document before the first word appears.
Is renting a GPU cheaper than buying the MacBook Pro 16" M5 Pro?
An A100 (80 GB) rents from $1.07/hr.