Llama 4 Scout 17B 16E Instruct on M3 Ultra 96 GB: VRAM, speed and fit
Llama 4 Scout 17B 16E Instruct at 4-bit runs on the M3 Ultra 96 GB with 32K of context at about 37 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 96 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 92.1 GB
- of 96.0 GB
- Context
- 32K
- auto
- Speed
- 37 tok/s
- 25 when full
- First reply
- 11 s
- 2K prompt
Where the memory goes
- Model
- 61.3 GB
- Context
- 6.0 GB
- Overhead
- 811 MB
- OS
- 24.0 GB
- Free
- 3.9 GB
- Memory
- 92.1 GB of 96.0 GB
- Context
- 32K tokens · auto
- Speed
- 37 tok/s · 25 when full
- First reply
- 11 s for a 2K prompt
- Running cost
- $3.55/mo at home · $122/mo on a cloud 4× RTX A4500
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 72.0 GB usable | 68.1 GB needed | Pass |
| Headroom | 5% free | 3.9 GB free (5%) | Pass |
| Context for chat | 16K or more | 32K | Pass |
| Writing speed | 15 tok/s or more | 37 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 11 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 4 Scout 17B 16E Instruct
- Parameters
- 109B, 18B active
- Precision
- 4-bit (Q4_K_M)
- Context
- 32K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M3 Ultra 96 GB
- GPU can use
- 72.0 GB of 96.0 GB
Worth trying
- 8-bit cache: Room for 60K context
Running cost
- At home
- $3.55/mo
- 162 W at the wall
- Renting instead
- $122/mo
- 4× RTX A4500 at $1.00/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 unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF- vLLM
vllm serve meta-llama/Llama-4-Scout-17B-16E-Instruct
Llama 4 Scout 17B 16E Instruct on similar machines
- Mac mini M4 Pro 48 GBJust misses
- Mac mini M4 Pro 64 GBRuns
- M4 Max 128 GBRuns
- M5 Max 128 GBRuns
- M3 Ultra 256 GBRuns
- M3 Ultra 512 GBRuns
- M5 Ultra 512 GBRuns
- Ryzen AI Max+ 395 64 GBRuns
All machines: Llama 4 Scout 17B 16E Instruct VRAM requirements. Everything that runs here: what can the M3 Ultra 96 GB run?
Other models that run on M3 Ultra 96 GB
Questions
Can Llama 4 Scout 17B 16E Instruct run on M3 Ultra 96 GB?
Llama 4 Scout 17B 16E Instruct at 4-bit runs on the M3 Ultra 96 GB with 32K of context at about 37 tokens a second.
Report VR-0A2VJAX, calculated Nov 22, 2026 from published specs, not benchmarked.