Llama 3.3 70B on M3 Ultra 256 GB: VRAM, speed and fit
Llama 3.3 70B at 8-bit runs on the M3 Ultra 256 GB with 128K of context at about 6.9 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 256 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 175 GB
- of 256 GB
- Context
- 128K
- auto
- Speed
- 6.9 tok/s
- 4.4 when full
- First reply
- 13 s
- 2K prompt
Where the memory goes
- Model
- 69.8 GB
- Context
- 40.0 GB
- Overhead
- 763 MB
- OS
- 64.0 GB
- Free
- 81.4 GB
- Memory
- 175 GB of 256 GB
- Context
- 128K tokens · auto
- Speed
- 6.9 tok/s · 4.4 when full
- First reply
- 13 s for a 2K prompt
- Running cost
- $3.55/mo at home · $287/mo on a cloud 4× A40
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 192 GB usable | 111 GB needed | Pass |
| Headroom | 5% free | 81.4 GB free (42%) | Pass |
| Context for chat | 16K or more | 128K | Pass |
| Writing speed | 15 tok/s or more | 6.9 tok/s | Check |
| First reply | under 3 s, 2K prompt | 13 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 3.3 70B
- Parameters
- 70.5B
- Precision
- 8-bit (Q8_0)
- Context
- 128K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M3 Ultra 256 GB
- GPU can use
- 192 GB of 256 GB
Running cost
- At home
- $3.55/mo
- 162 W at the wall
- Renting instead
- $287/mo
- 4× A40 at $2.36/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
- Ollama
ollama run llama3.3:70b- llama.cpp
llama-server -hf unsloth/Llama-3.3-70B-Instruct-GGUF- vLLM
vllm serve meta-llama/Llama-3.3-70B-Instruct- MLX (Mac)
mlx_lm.chat --model mlx-community/Llama-3.3-70B-Instruct-4bit
Llama 3.3 70B on similar machines
- Mac mini M4 Pro 64 GBRuns
- M4 Max 128 GBRuns
- M5 Max 128 GBRuns
- M3 Ultra 96 GBRuns
- M3 Ultra 512 GBRuns
- M5 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBRuns
- Ryzen AI Max+ 395 128 GBRuns
All machines: Llama 3.3 70B VRAM requirements. Everything that runs here: what can the M3 Ultra 256 GB run?
Other models that run on M3 Ultra 256 GB
Questions
Can Llama 3.3 70B run on M3 Ultra 256 GB?
Llama 3.3 70B at 8-bit runs on the M3 Ultra 256 GB with 128K of context at about 6.9 tokens a second.
Report VR-0O8TFN9, calculated Nov 22, 2026 from published specs, not benchmarked.