Can I Run SmolLM2 on MacBook Pro 16" (M5 Max, 128 GB)?
Written by Jakub Rusinowski · Last updated November 20, 2024
Yes — comfortably
Yes, comfortably — SmolLM2 1.7B Instruct at Q8_0 needs about 4.2 GB of the 96 GB usable on MacBook Pro 16" (M5 Max, 128 GB), leaving ~91.8 GB spare and running at ~92.7 tok/s (estimated), with room for about 8,192 tokens of context.
Confidence: high · Recommended quantization: Q8_0 · Estimated speed: ~92.7 tok/s
See what else this hardware can run →
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
MacBook Pro 16" (M5 Max, 128 GB) — what it gives a model
| Usable memory for models | 96 GB |
| Memory bandwidth | 614 GB/s |
| Form factor | Laptop |
| Operating system | macOS |
| Memory upgradeable | No — soldered |
SmolLM2 on MacBook Pro 16" (M5 Max, 128 GB): memory by quantization
| Quant | Memory needed | Fits 96 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 5.8 GB | ✓ Yes | 8K | ~64.3 tok/s | 3.4 GB |
| Q8_0 | 4.2 GB | ✓ Yes | 8K | ~92.7 tok/s | 1.8 GB |
| Q6_K | 3.8 GB | ✓ Yes | 8K | ~104.6 tok/s | 1.4 GB |
| Q5_K_M | 3.6 GB | ✓ Yes | 8K | ~111.2 tok/s | 1.2 GB |
| Q4_K_M | 3.4 GB | ✓ Yes | 8K | ~118.2 tok/s | 1 GB |
| Q3_K_M | 3.1 GB | ✓ Yes | 8K | ~132.3 tok/s | 0.7 GB |
| Q2_K | 3 GB | ✓ Yes | 8K | ~141.6 tok/s | 0.6 GB |
Which SmolLM2 sizes fit
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| SmolLM2 1.7B Instruct | 3.4 GB | ✓ Fits | ~118.2 tok/s |
| SmolLM2 360M Instruct | 1.4 GB | ✓ Fits | ~241.1 tok/s |
What to watch out for
- Memory on this machine is not upgradeable, so the configuration you buy is the ceiling for every model you will ever run on it.
MacBook Pro M5 Max 128 GB limitations
- Unified memory is soldered and cannot be upgraded after purchase.
Recommended setup
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
How these numbers are calculated
- Memory need = quantized weights + KV cache at 8,192 tokens (f16) + 0.8 GB runtime overhead.
- 128 GB unified memory at 614 GB/s, shared between CPU and GPU.
- macOS reserves a share of unified memory for the system, so not all of it is available to a model.
- Throughput is a memory-bandwidth roofline estimate, not a measurement. It is labelled "estimated" everywhere it appears.
- KV cache is computed from this model's published attention configuration.
FAQ
Can I run SmolLM2 on MacBook Pro 16" (M5 Max, 128 GB)?
Yes, comfortably — SmolLM2 1.7B Instruct at Q8_0 needs about 4.2 GB of the 96 GB usable on MacBook Pro 16" (M5 Max, 128 GB), leaving ~91.8 GB spare and running at ~92.7 tok/s (estimated), with room for about 8,192 tokens of context.
Which quantization of SmolLM2 should I use on MacBook Pro 16" (M5 Max, 128 GB)?
Q8_0 — it needs about 4.2 GB of the 96 GB available, downloads as roughly 1.8 GB, and runs at an estimated 92.7 tokens/sec with up to 8K of context.
What limits SmolLM2 on MacBook Pro 16" (M5 Max, 128 GB)?
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Which runtime should I use?
Ollama or LM Studio (Metal) — MLX for the fastest Apple-native throughput
Other Computers
- SmolLM2 on MacBook Pro M4 Max 128 GB
- SmolLM2 on MacBook Pro M4 Max 48 GB
- SmolLM2 on MacBook Pro M4 Pro 24 GB
- SmolLM2 on MacBook Air M4 16 GB
Other Models on MacBook Pro 16" (M5 Max, 128 GB)
- SmolLM3 on MacBook Pro 16" (M5 Max, 128 GB)
- StarCoder 2 on MacBook Pro 16" (M5 Max, 128 GB)
- Aya 3B (Tiny Aya) on MacBook Pro 16" (M5 Max, 128 GB)
- VibeThinker on MacBook Pro 16" (M5 Max, 128 GB)
- Yi 1.5 Family on MacBook Pro 16" (M5 Max, 128 GB)
SmolLM2 on GPUs
- SmolLM2 on NVIDIA GeForce RTX 5060 Ti 8GB
- SmolLM2 on NVIDIA GeForce RTX 5060
- SmolLM2 on NVIDIA GeForce RTX 4060