DeepSeek R1 Distill Qwen 32B on Mac mini M4 24 GB: VRAM, speed and fit
DeepSeek R1 Distill Qwen 32B at 4-bit needs 21.2 GB; the M4 24 GB can use 16.0 GB. The smallest machine we checked that runs it is the RTX 5090.
Text generation · Chat · Ollama / LM Studio
Won’t fit · on M4 24 GB · 4-bit (Q4_K_M) · Ollama / LM Studio · Chat
- GPU memory
- 29.2 GB
- of 24.0 GB
- Context
- 8K
- auto
- Speed
- n/a
- First reply
- n/a
Where the memory goes
- Model
- 18.5 GB
- Context
- 2.0 GB
- Overhead
- 713 MB
- OS
- 8.0 GB
- Over by
- 5.2 GB
- Memory
- 29.2 GB of 24.0 GB
- Context
- 8K tokens · auto
- Speed
- Doesn’t run here
- Running cost
- Doesn’t run here · $33/mo on a cloud RTX A5000
Validation: Not validated
| Check | Target | Result | Status |
|---|---|---|---|
| Fits in GPU memory | 16.0 GB usable | 21.2 GB needed | Fails |
| Headroom | 5% free | none | Fails |
| Context for chat | 16K or more | – | Not run |
| Writing speed | 15 tok/s or more | – | Not run |
| First reply | under 3 s, 2K prompt | – | Not run |
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 32B
- Parameters
- 32.8B
- Precision
- 4-bit (Q4_K_M)
- Context
- 8K, auto
- Chats at once
- 1
- Use
- Chat
- Runs in
- Ollama / LM Studio
- Hardware
- M4 24 GB
- GPU can use
- 16.0 GB of 24.0 GB
Worth trying
- RTX 5090: Runs it with 40K context
- M5 Max · 48 GB: Runs it with 56K context
- Ryzen AI Max+ 395 · 64 GB: Runs it with 104K context
Running cost
- At home
- n/a
- Doesn’t run on this machine.
- 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 21, 2026.
How to run it
- llama.cpp
llama-server -hf bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF- vLLM
vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-32B- MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-R1-Distill-Qwen-32B-4bit
DeepSeek R1 Distill Qwen 32B on similar machines
- 2× RTX 5090Runs
- 4× RTX 3090Runs
- RTX PRO 6000 BlackwellRuns
- Mac mini M4 16 GBToo big
- Mac mini M4 32 GBRuns
- Mac mini M4 Pro 24 GBJust misses
- Mac mini M4 Pro 48 GBRuns
- Mac mini M4 Pro 64 GBRuns
All machines: DeepSeek R1 Distill Qwen 32B VRAM requirements. Everything that runs here: what can the Mac mini M4 24 GB run?
Other models that run on Mac mini M4 24 GB
Questions
Can DeepSeek R1 Distill Qwen 32B run on Mac mini M4 24 GB?
DeepSeek R1 Distill Qwen 32B at 4-bit needs 21.2 GB; the M4 24 GB can use 16.0 GB. The smallest machine we checked that runs it is the RTX 5090.
Shown at the closest setup. Report VR-0LSG9G4, calculated Nov 22, 2026 from published specs, not benchmarked.