Llama Guard 4 12B on Mac mini M4 Pro 48 GB: VRAM, speed and fit
Llama Guard 4 12B at 8-bit runs on the M4 Pro 48 GB with 112K of context at about 18 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M4 Pro 48 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 45.7 GB
- of 48.0 GB
- Context
- 112K
- auto
- Speed
- 18 tok/s
- 6.4 when full
- First reply
- 7.1 s
- 2K prompt
Where the memory goes
- Model
- 11.9 GB
- Context
- 21.0 GB
- Overhead
- 811 MB
- OS
- 12.0 GB
- Free
- 2.3 GB
- Memory
- 45.7 GB of 48.0 GB
- Context
- 112K tokens · auto
- Speed
- 18 tok/s · 6.4 when full
- First reply
- 7.1 s for a 2K prompt
- Running cost
- $1.84/mo at home · $61/mo on a cloud 2× RTX A4500
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 36.0 GB usable | 33.7 GB needed | Pass |
| Headroom | 5% free | 2.3 GB free (6%) | Pass |
| Context for chat | 16K or more | 112K | Pass |
| Writing speed | 15 tok/s or more | 18 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 7.1 s | Fails |
Targets: a reply you can read along with, a first reply the use case tolerates, and 5% of memory left free. Calculated from published specs, not benchmarked.
The setup
- Model
- Llama Guard 4 12B
- Parameters
- 12B
- Precision
- 8-bit (Q8_0)
- Context
- 112K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M4 Pro 48 GB
- GPU can use
- 36.0 GB of 48.0 GB
Running cost
- At home
- $1.84/mo
- 84 W at the wall
- Renting instead
- $61/mo
- 2× RTX A4500 at $0.50/h
4 h a day, power at $0.18 per kWh, cloud at RunPod on-demand prices as of Nov 22, 2026.
How to run it
- llama.cpp
llama-server -hf DevQuasar/meta-llama.Llama-Guard-4-12B-GGUF- vLLM
vllm serve meta-llama/Llama-Guard-4-12B
Llama Guard 4 12B on similar machines
- Mac mini M4 16 GBRuns
- Mac mini M4 24 GBRuns
- Mac mini M4 32 GBRuns
- Mac mini M4 Pro 24 GBRuns
- Mac mini M4 Pro 64 GBRuns
- M4 Max 128 GBRuns
- M5 Max 128 GBRuns
- M3 Ultra 96 GBRuns
All machines: Llama Guard 4 12B VRAM requirements. Everything that runs here: what can the Mac mini M4 Pro 48 GB run?
Other models that run on Mac mini M4 Pro 48 GB
Questions
Can Llama Guard 4 12B run on Mac mini M4 Pro 48 GB?
Llama Guard 4 12B at 8-bit runs on the M4 Pro 48 GB with 112K of context at about 18 tokens a second.
Report VR-1VAYCD3, calculated Nov 22, 2026 from published specs, not benchmarked.