llmrun

Apple · M3 Max · Laptop

Best AI Models for MacBook Pro 16" M3 Max (36 GB)

Runs 14B and 35B MoE models well; dense 27–31B fits but is slow at 12 tok/s, and 70B doesn't fit in 32.5 GB.

36 GB unified32.5 GB for models300 GB/s22 TFLOPS FP162023
Memory
36 GB48 GB64 GB96 GB128 GB
Same chip in
MacBook Pro 16"MacBook Pro 14"

What LLMs can the MacBook Pro 16" M3 Max run?

#ModelSpeedllmrun ScoreQuant · Memory
1
Qwen3.6 35B A3BAlibabaHow to run →
Q4_K_M · 22.0 GB
45.9 tok/sQ4_K_M · 22.0 GB
2
Gemma 4 26B A4B ITGoogle
Q4_K_M · 16.5 GB
52.4 tok/sQ4_K_M · 16.5 GB
3
Qwen3 30B A3B Thinking 2507Alibaba
Q4_K_M · 19.4 GB
51.6 tok/sQ4_K_M · 19.4 GB
4
GPT OSS 20BOpenAI
Q4_K_M · 13.1 GB
58.4 tok/sQ4_K_M · 13.1 GB
5
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA
Q4_K_M · 19.3 GB
57.9 tok/sQ4_K_M · 19.3 GB
See all 316 models on the MacBook Pro 16" M3 Max →Bars = traction for models without a Score yet
Task rankings use that task's benchmarks, topped up from Overall when short; bars mark well-known models with no Score yet.

About the MacBook Pro 16" M3 Max (36 GB)

The MacBook Pro 16" M3 Max is a 36 GB laptop with more memory than speed: it runs 14B and 35B MoE models well. Among 36 GB machines, only the M5 Max and M4 Max write faster. macOS keeps about 3.5 GB, leaving 32.5 GB for models. Prompt reading is its weak spot: a 4K-token prompt waits 9.0 s before the first word on Qwen3.6 35B A3B. M3 Max generation, released 2023; the newer M4 Max writes 20% faster with 1.2× the compute.

Speed in 36 GB#3300 GB/s
Prompt reading#322 TFLOPS
For models32.5 GBmacOS keeps 3.5 GB
ChipM3 Maxreleased 2023

MacBook Pro 16" M3 Max strengths and weaknesses

Strengths

  • Runs 35B MoE models: Qwen3.6 35B A3B at 45.9 tok/s in 22 GB

Weaknesses

  • 70B models don't fit: Llama 3.3 70B Instruct needs 51.3 GB at Q4 vs 32.5 GB usable here
  • Slow on large dense models: Qwen3.8 27B at 12.1 tok/s
  • Slow prompt reading: A 32K-token prompt on Qwen3.6 35B A3B waits 1.2 min for the first token
  • No CUDA: vLLM, AWQ, GPTQ and FP8 builds don't run; use GGUF or MLX

Memory for models

32.5 GB of 36 GB
9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE22 GB
14B11.9 GB35B MoE22 GB
For models 32.5 GBmacOS keeps 3.5 GBModel size at Q4

70B models need 51.3 GB at Q4, more than the 32.5 GB available. The 48 GB config fits Qwen3.8 27B →

Similar devices and alternatives

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.

Same chip, 12 GB more memoryMacBook Pro 16" M3 Max (48 GB)Apple · 44.5 GB for models · M3 Max
▲ 20% speed▲ 12 GBno price
Same familySame chip, 28 GB more memoryMacBook Pro 16" M3 Max (64 GB)Apple · 60.5 GB for models · M3 Max
▲ 20% speed▲ 28 GBno price
Same family20% faster, same memoryMac Studio M4 Max (36 GB)Apple · 32.5 GB for models · M4 Max
▲ 20% speedsame memoryabout $2,499
Newer machine, 49% slowerMac Mini M4 (32 GB)Apple · 28.5 GB for models · M4
▼ 49% speed▼ 4 GBabout $999
Newer laptop, 38% slowerMacBook Pro 14 M5Apple · 24 GB for models · M5
▼ 38% speed▼ 8.5 GBabout $1,839
Reads prompts 22× faster, 32 GB for modelsRTX 5090NVIDIA · 32 GB VRAM · GPU
▲ 22× prompts▲ 365% speedsame memoryabout $5,376rent $0.64/hr

MacBook Pro 16" M3 Max tokens per second by model size

Output speed depends on memory bandwidth (300 GB/s). Grey rows need more than the 32.5 GB available.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    33.0tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB
    22.1tok/s
  3. 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
    12.1tok/s
  4. 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
    45.9tok/s
  5. 70BLlama 3.3 70B Instruct · does not fit
    needs 51.3 GB
  6. 120B MoEGPT OSS 120B · does not fit
    needs 70.8 GB

Estimated speeds: Q4_K_M, 4K context, one user. How we estimate

Max generations: writing vs compute

M1 Max → M5 Max
Writing speed (tok/s)Compute (TFLOPS FP16)
1×2×3×M1 Max2021M2 Max2023M3 Max2023M4 Max2024M5 Max2026M1 Max · 20.8 TFLOPS FP16M1 Max · 54.5 tok/s · 400 GB/sM2 Max · 27.2 TFLOPS FP16M2 Max · 54.5 tok/s · 400 GB/sM3 Max · 21.5 TFLOPS FP16M3 Max · 45.9 tok/s · 300 GB/sM4 Max · 25.8 TFLOPS FP16M4 Max · 55.2 tok/s · 409.6 GB/sM5 Max · 54.4 TFLOPS FP16M5 Max · 58.8 tok/s · 460 GB/sCompute 2.6×Writing +8%
1×2×3×M12021M22023M32023M42024M52026M1 Max · 20.8 TFLOPS FP16M1 Max · 54.5 tok/s · 400 GB/sM2 Max · 27.2 TFLOPS FP16M2 Max · 54.5 tok/s · 400 GB/sM3 Max · 21.5 TFLOPS FP16M3 Max · 45.9 tok/s · 300 GB/sM4 Max · 25.8 TFLOPS FP16M4 Max · 55.2 tok/s · 409.6 GB/sM5 Max · 54.4 TFLOPS FP16M5 Max · 58.8 tok/s · 460 GB/sCompute 2.6×Writing +8%

Writing speed follows memory bandwidth and barely moved: 54.5 to 58.8 tok/s since the M1 Max. Compute, which sets how fast prompts are read, grew 2.6×. Indexed to the M1 Max; speeds on Qwen3.6 35B A3B, same 32 GB.

All 1115 models on the MacBook Pro 16" M3 Max

Featured only

Best quant that fits in 32.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with MacBook Pro 16" M3 Max (36 GB) — ranked by Score, recency and Fit
ModelVRAMScoreFit
Neural Chat 7B v3 3
7.2B·Q4_K_M·42.8 t/s·33K ctx
6.8 GBA77, Runs well
Llama Guard 3 1B
1.5B·Q4_K_M·212.1 t/s
2.6 GBS100, Runs great
Nous Hermes 2 Mixtral 8x7B DPO
46.7B·Q4_K_M·22.8 t/s·33K ctx
30.5 GBC42, Usable
GPT Neox Japanese 2.7B
2.7B·BF16·35.4 t/s·2K ctx
5.9 GBA73, Runs well
Orca Mini 3B
3.4B·Q4_K_M·92.9 t/s·2K ctx
2.3 GBS90, Runs great
Qwen1.5 0.5B Chat
620M·Q4_K_M·241.4 t/s·33K ctx
2.3 GBS100, Runs great
T5gemma 2B 2B Ul2 IT
5.6B·Q4_K_M·56.9 t/s
6.0 GBA82, Runs well
Qwen2.5 Coder 1.5B Instruct
1.5B·Q4_K_M·164.1 t/s·33K ctx
1.7 GBS97, Runs great
Llama 3 3 Nemotron Super 49B V1
49.9B·Q3_K_L·7.5 t/s·131K ctx
32.4 GBF13, Won't fit
Kimi Linear 48B A3B Base
49.1B·Q4_K_S·66.6 t/s
32.0 GBC44, Usable
Granite 4.0 Tiny Preview
6.7B·Q4_K_M·80.5 t/s·131K ctx
5.6 GBS88, Runs great
Gemma 3 12B Pt
12.2B·Q4_K_M·26.1 t/s
10.9 GBA67, Runs well
Qwen2.5 Coder 3B Instruct
3.1B·Q4_K_M·94.2 t/s·33K ctx
2.8 GBS90, Runs great
Llama 3.1 Nemotron Safety Guard 8B v3
8.0B·Q4_K_M·39.0 t/s·131K ctx
7.3 GBA75, Runs well
Llama 3.1 Nemotron Nano 8B V1
8B·Q4_K_M·39.1 t/s·131K ctx
7.3 GBA75, Runs well

MacBook Pro 16" M3 Max specs

Specs

Chip
M3 Max
CPU cores
14
GPU cores
30
Unified memory
36 GB
For models
32.5 GB (macOS keeps 3.5 GB)
Memory bandwidth
300 GB/s
FP16 (dense)
21.5 TFLOPS
Neural Engine
18 TOPS
Released
2023-11-07

MacBook Pro 16" M3 Max FAQ

How much memory is available for AI on the MacBook Pro 16" M3 Max (36 GB)?

About 32.5 GB of the 36 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the MacBook Pro 16" M3 Max (36 GB) can run?

Qwen3.6 35B A3B (36.0B) at Q4_K_M uses 22.0 GB, 68% of the available memory, and runs at about 45.9 tok/s.

Can the MacBook Pro 16" M3 Max (36 GB) run 70B models?

No. Llama 3.3 70B Instruct needs 51.3 GB at Q4, more than the 32.5 GB available.

How long does the MacBook Pro 16" M3 Max (36 GB) take to read a long prompt?

On Qwen3.6 35B A3B, about 9.0 s for a 4K-token prompt and 72 s for a 32K-token document before the first word appears.

Is renting a GPU cheaper than buying the MacBook Pro 16" M3 Max?

An A40 (48 GB) rents from $0.35/hr.

24 GB GPUsAll MacsLaptopsMac Studio M5 MaxMacBook Pro 14" M5 MaxMacBook Pro 16" M5 MaxMacBook Pro 14" M4 MaxMacBook Pro 16" M4 MaxMacBook Pro 16" M4 MaxBest coding LLMsAll hardware