Qwen3 14B on M3 Ultra 96 GB: VRAM, speed and fit
Qwen3 14B at 8-bit runs on the M3 Ultra 96 GB with 40K of context at about 32 tokens a second.
Text generation · Chat · Ollama / LM Studio
Runs comfortably · on M3 Ultra 96 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat
- GPU memory
- 45.6 GB
- of 96.0 GB
- Context
- 40K
- auto
- Speed
- 32 tok/s
- 23 when full
- First reply
- 2.6 s
- 2K prompt
Where the memory goes
- Model
- 14.6 GB
- Context
- 6.3 GB
- Overhead
- 713 MB
- OS
- 24.0 GB
- Free
- 50.4 GB
- Memory
- 45.6 GB of 96.0 GB
- Context
- 40K tokens · auto
- Speed
- 32 tok/s · 23 when full
- First reply
- 2.6 s for a 2K prompt
- Running cost
- $3.55/mo at home · $33/mo on a cloud RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 72.0 GB usable | 21.6 GB needed | Pass |
| Headroom | 5% free | 50.4 GB free (70%) | Pass |
| Context for chat | 16K or more | 40K | Pass |
| Writing speed | 15 tok/s or more | 32 tok/s | Pass |
| First reply | under 3 s, 2K prompt | 2.6 s | Pass |
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
- Qwen3 14B
- Parameters
- 14.8B
- Precision
- 8-bit (Q8_0)
- Context
- 40K, 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
Running cost
- At home
- $3.55/mo
- 162 W at the wall
- Renting instead
- $33/mo
- RTX A5000 at $0.27/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 Qwen/Qwen3-14B-GGUF- vLLM
vllm serve Qwen/Qwen3-14B- MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3-14B-4bit- Model card
- huggingface.co/Qwen/Qwen3-14B
Qwen3 14B on similar machines
- Mac mini M4 Pro 48 GBRuns
- 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: Qwen3 14B 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 Qwen3 14B run on M3 Ultra 96 GB?
Qwen3 14B at 8-bit runs on the M3 Ultra 96 GB with 40K of context at about 32 tokens a second.
Report VR-0F8K3EQ, calculated Nov 22, 2026 from published specs, not benchmarked.