DeepSeek R1 Distill Qwen 14B on M3 Ultra 96 GB: VRAM, speed and fit
DeepSeek R1 Distill Qwen 14B at 8-bit runs on the M3 Ultra 96 GB with 128K of context at about 31 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
- 63.3 GB
- of 96.0 GB
- Context
- 128K
- auto
- Speed
- 31 tok/s
- 12 when full
- First reply
- 2.6 s
- 2K prompt
Where the memory goes
- Model
- 14.6 GB
- Context
- 24.0 GB
- Overhead
- 713 MB
- OS
- 24.0 GB
- Free
- 32.7 GB
- Memory
- 63.3 GB of 96.0 GB
- Context
- 128K tokens · auto
- Speed
- 31 tok/s · 12 when full
- First reply
- 2.6 s for a 2K prompt
- Running cost
- $3.55/mo at home · $66/mo on a cloud 2× RTX A5000
Validation: Validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 72.0 GB usable | 39.3 GB needed | Pass |
| Headroom | 5% free | 32.7 GB free (45%) | Pass |
| Context for chat | 16K or more | 128K | Pass |
| Writing speed | 15 tok/s or more | 31 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
- DeepSeek R1 Distill Qwen 14B
- Parameters
- 14.8B
- Precision
- 8-bit (Q8_0)
- Context
- 128K, 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
- $66/mo
- 2× RTX A5000 at $0.54/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 bartowski/DeepSeek-R1-Distill-Qwen-14B-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-14B- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-R1-Distill-Qwen-14B-4bit
DeepSeek R1 Distill Qwen 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: DeepSeek R1 Distill Qwen 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 DeepSeek R1 Distill Qwen 14B run on M3 Ultra 96 GB?
DeepSeek R1 Distill Qwen 14B at 8-bit runs on the M3 Ultra 96 GB with 128K of context at about 31 tokens a second.
Report VR-0737PY2, calculated Nov 22, 2026 from published specs, not benchmarked.