llmrun

Apple · M5 Pro · Laptop

Best AI Models for MacBook Pro 16" M5 Pro (48 GB)

Runs 14B and 35B MoE models well; dense 27–31B fits but is slow at 12 tok/s, and 70B only just fits in 44.5 GB.

48 GB unified44.5 GB for models307 GB/s32 TFLOPS FP162026
Memory
24 GB48 GB64 GB
Same chip in
MacBook Pro 16"MacBook Pro 14-inchabout $2,299Mac MiniMacBook Pro 14"

Top models by task

#ModelSpeed ↓llmrun ScoreQuant · Memory
1
GPT OSS 20BOpenAIHow to run →
Q4_K_M · 13.1 GB
59.3 tok/sQ4_K_M · 13.1 GB
2
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16NVIDIA
Q4_K_M · 19.3 GB
58.4 tok/sQ4_K_M · 19.3 GB
3
Gemma 4 26B A4B ITGoogle
Q4_K_M · 16.5 GB
53.2 tok/sQ4_K_M · 16.5 GB
4
Qwen3 30B A3B Thinking 2507Alibaba
Q4_K_M · 19.4 GB
52.2 tok/sQ4_K_M · 19.4 GB
5
Qwen3 30B A3B Instruct 2507Alibaba
Q4_K_M · 19.4 GB
52.2 tok/sQ4_K_M · 19.4 GB
See all 335 models on the MacBook Pro 16" M5 Pro →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" M5 Pro (48 GB)

The MacBook Pro 16" M5 Pro is a 48 GB laptop with more memory than speed: it runs 14B and 35B MoE models well. Among 48 GB machines, only the M5 Max, M4 Max and M3 Max write faster. macOS keeps about 3.5 GB, leaving 44.5 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.

Speed in 48 GB#4307 GB/s
Prompt reading#332 TFLOPS
For models44.5 GBmacOS keeps 3.5 GB
ChipM5 Proreleased 2026

MacBook Pro 16" M5 Pro strengths and weaknesses

Strengths

  • Runs 35B MoE models: Qwen3.6 35B A3B at 46.5 tok/s in 22 GB

Weaknesses

  • 120B MoE models don't fit: GPT OSS 120B needs 70.8 GB at Q4 vs 44.5 GB usable here
  • Slow on large dense models: Llama 3.3 70B Instruct at 5.4 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

44.5 GB of 48 GB
9B6.6 GB14B11.9 GB27–31B17.9 GB35B MoE22 GB70B44.5 GB
35B MoE22 GB70B44.5 GB
For models 44.5 GBmacOS keeps 3.5 GBModel size at Q4

120B MoE models need 70.8 GB at Q4, more than the 44.5 GB available.

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 Qwen3.5 9B.

Same chip, 24 GB less memoryMacBook Pro 16" M5 Pro (24 GB)Apple · 20.5 GB for models · M5 Pro
same speed▼ 24 GBno price
Same familySame chip, 16 GB more memoryMacBook Pro 16" M5 Pro (64 GB)Apple · 60.5 GB for models · M5 Pro
same speed▲ 16 GBno price
Same family78% faster, same memoryMacBook Pro 16" M4 Max (48 GB)Apple · 44.5 GB for models · M4 Max
▲ 78% speedsame memoryabout $3,999
Machine, 11% slowerMac Mini M4 Pro (48 GB)Apple · 44.5 GB for models · M4 Pro
▼ 11% speedsame memoryabout $2,199
167% faster, 27.5 GB more memoryMac Studio M3 Ultra (96 GB)Apple · 72 GB for models · M3 Ultra
▲ 167% speed▲ 27.5 GBabout $3,999
3.0× faster if your models fit in 24 GBRTX 4090NVIDIA · 24 GB VRAM · GPU
▲ 205% speed▼ 20.5 GBabout $1,599rent $0.34/hr

MacBook Pro 16" M5 Pro tokens per second by model size

Output speed depends on memory bandwidth (307 GB/s). Grey rows need more than the 44.5 GB available.

  1. 9BQwen3.5 9B · Q4_K_M · 6.6 GB
    33.8tok/s
  2. 14BQwen3 14B · Q4_K_M · 11.9 GB
    22.6tok/s
  3. 27–31BQwen3.8 27B · Q4_K_M · 17.9 GB
    12.3tok/s
  4. 35B MoEQwen3.6 35B A3B · Q4_K_M · 22.0 GB
    46.5tok/s
  5. 70BLlama 3.3 70B Instruct · Q3_K_L · 44.5 GB tight · Q3_K_L
    5.4tok/s
  6. 120B MoEGPT OSS 120B · does not fit
    needs 70.8 GB

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

Pro generations: writing vs compute

M1 Pro → M5 Pro
Writing speed (tok/s)Compute (TFLOPS FP16)
1×2×3×4×M1 Pro2021M2 Pro2023M3 Pro2023M4 Pro2024M5 Pro2026M1 Pro · 10.4 TFLOPS FP16M1 Pro · 22.0 tok/s · 200 GB/sM2 Pro · 13.6 TFLOPS FP16M2 Pro · 22.0 tok/s · 200 GB/sM3 Pro · 12.9 TFLOPS FP16M3 Pro · 16.5 tok/s · 150 GB/sM4 Pro · 17.2 TFLOPS FP16M4 Pro · 30.0 tok/s · 273 GB/sM5 Pro · 32.3 TFLOPS FP16M5 Pro · 33.8 tok/s · 307 GB/sCompute 3.1×Writing +54%
1×2×3×4×M12021M22023M32023M42024M52026M1 Pro · 10.4 TFLOPS FP16M1 Pro · 22.0 tok/s · 200 GB/sM2 Pro · 13.6 TFLOPS FP16M2 Pro · 22.0 tok/s · 200 GB/sM3 Pro · 12.9 TFLOPS FP16M3 Pro · 16.5 tok/s · 150 GB/sM4 Pro · 17.2 TFLOPS FP16M4 Pro · 30.0 tok/s · 273 GB/sM5 Pro · 32.3 TFLOPS FP16M5 Pro · 33.8 tok/s · 307 GB/sCompute 3.1×Writing +54%

Writing 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 335 models on the MacBook Pro 16" M5 Pro

Featured only

Best quant that fits in 44.5 GB, ordered by llmrun Score. Fit grades how well it runs here, S best. How ranking works

LLM models compatible with MacBook Pro 16" M5 Pro (48 GB) — ranked by Score, recency and Fit
ModelVRAMScoreFit
Qwen3.8 27B
27.8B·Q4_K_M·12.3 t/s·262K ctx
17.9 GBB51, Decent
Qwen3.6 35B A3B
36.0B·Q4_K_M·46.5 t/s·262K ctx
22.0 GBA78, Runs well
Gemma 4 26B A4B IT
25.8B·Q4_K_M·53.2 t/s·262K ctx
16.5 GBA81, Runs well
NVIDIA Nemotron 3.5 Lightning 30B A3B BF16
31.6B·Q4_K_M·58.4 t/s·262K ctx
19.3 GBA83, Runs well
Muse Glimmer 30B
29.8B·Q4_K_M·11.7 t/s·131K ctx
19.6 GBB50, Decent
GLM 4.7 Flash
31.2B·Q4_K_M·43.5 t/s·203K ctx
19.9 GBA77, Runs well
Gemma 4 31B IT
31.3B·Q4_K_M·10.5 t/s·262K ctx
21.7 GBB49, Decent
JEV 27B VL
27.8B·Q4_K_M·12.3 t/s·262K ctx
17.9 GBB51, Decent
MiniCPM5 2B
2.5B·Q4_K_M·113.1 t/s·131K ctx
2.5 GBS94, Runs great
Ornith 1.5 35B A3B
36.0B·Q4_K_M·46.5 t/s·262K ctx
22.0 GBA78, Runs well
Ling 3.0 Tiny
7.9B·Q4_K_M·109.3 t/s·131K ctx
5.5 GBS93, Runs great
Qwen3.5 9B
9.7B·Q4_K_M·33.8 t/s·262K ctx
6.6 GBA73, Runs well
MiMo V2.6 Distill Qwen 9B
9.4B·Q4_K_M·34.6 t/s·262K ctx
6.5 GBA73, Runs well
Ornith 1.0 35B
35.1B·Q4_K_M·52.4 t/s·262K ctx
21.5 GBA81, Runs well
LFM2.5 8B A1B
8.5B·Q4_K_M·101.3 t/s·128K ctx
5.6 GBS92, Runs great

MacBook Pro 16" M5 Pro specs

Specs

Chip
M5 Pro
CPU cores
18
GPU cores
20
Unified memory
48 GB
For models
44.5 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 (48 GB)?

About 44.5 GB of the 48 GB. macOS keeps roughly 3.5 GB for itself and other apps.

What is the largest model the MacBook Pro 16" M5 Pro (48 GB) can run?

Qwen3.6 35B A3B (36.0B) at Q4_K_M uses 22.0 GB, 50% of the available memory, and runs at about 46.5 tok/s.

Can the MacBook Pro 16" M5 Pro (48 GB) run 120B MoE models?

No. GPT OSS 120B needs 70.8 GB at Q4, more than the 44.5 GB available.

How long does the MacBook Pro 16" M5 Pro (48 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 A40 (48 GB) rents from $0.35/hr.

24 GB GPUsAll MacsLaptopsMac Studio M5 MaxMacBook Pro 14" M5 MaxMacBook Pro 16" M5 MaxMac Studio M4 MaxMacBook Pro 14" M4 MaxMac Studio M2 MaxMac Studio M4 MaxBest coding LLMsAll hardware