Will It Run AI
CalculatorModelsHardwareCompare
Product
  • Calculator
  • Compare
  • Tier List
Browse
  • Models
  • Hardware
  • Docs
About
  • Why It Works
  • What's New
  • Legal Notice
  • Privacy Policy

All estimates are approximations based on mathematical models and public specifications. Actual performance may vary. Do not make purchasing decisions based solely on these estimates.

Data sourced from Hugging Face, Ollama, and official model documentation. Model names and logos are trademarks of their respective owners.

© 2026 Will It Run AI — Fase Consulting Ibiza, S.L. (NIF: B57969656)

Home/Llama 3.2 3B Instruct/on Mac Studio M2 Ultra 64GB

Can it run?

Can Mac Studio M2 Ultra 64GB run Llama 3.2 3B Instruct?

CUsable

Runs well

Using Q5_K_M in Ollama

Capabilities:

Fit status

Runs well

Decode

219.1 tok/s

TTFT

884 ms

Safe context

67K

Memory

11.1 GB / 46.1 GB

Memory breakdown

Weights2.2 GB
KV Cache0.8 GB
Runtime1.2 GB
Headroom6.9 GB

Performance by workload

WorkloadGradeFitDecodeTTFTContext
Agentic CodingCRuns well219.1 tok/s1285 ms132K
ChatCRuns well219.1 tok/s482 ms33K
CodingCRuns well219.1 tok/s884 ms67K
RAGCRuns well219.1 tok/s1606 ms132K
ReasoningCRuns well219.1 tok/s1044 ms67K

Quantization options

How Llama 3.2 3B Instruct (3B params) fits at each quantization level on Mac Studio M2 Ultra 64GB (46.1 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
1.2 GB
LowD30
Q3_K_S
3
1.5 GB
LowD30
NVFP4
4
1.7 GB
MediumD30
Q4_K_M
4
1.8 GB
MediumD30
Q5_K_M
5
2.2 GB
HighD31
Q6_K
6
2.5 GB
HighD31
Q8_0
8
3.2 GB
Very HighD31
F16Best for your GPU
16
6.1 GB
MaximumD32

Get started

HuggingFace
huggingface-cli download hf-bartowski--llama-3-2-3b-instruct-gguf
See all results for Mac Studio M2 Ultra 64GBSee all hardware for Llama 3.2 3B Instruct