Skip to content

DeepSeek R1 0528 Qwen3 8B on Mac mini M4 16 GB: VRAM, speed and fit

DeepSeek R1 0528 Qwen3 8B at 6-bit runs on the M4 16 GB with 20K of context at about 15 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M4 16 GB · 6-bit (Q6_K) · Ollama / LM Studio · Chat

GPU memory
15.1 GB
of 16.0 GB
Context
20K
auto
Speed
15 tok/s
10 when full
First reply
9.9 s
2K prompt

Where the memory goes

Model
6.3 GB
Context
2.8 GB
Overhead
681 MB
OS
5.3 GB
Free
957 MB
Memory
15.1 GB of 16.0 GB
Context
20K tokens · auto
Speed
15 tok/s · 10 when full
First reply
9.9 s for a 2K prompt
Running cost
$0.85/mo at home · $29/mo on a cloud RTX 2000 Ada

Validation: Not validated

What DeepSeek R1 0528 Qwen3 8B on Mac mini M4 16 GB was checked against
CheckTargetResultStatus
Fits in GPU memory10.7 GB usable9.7 GB neededPass
Headroom5% free957 MB free (9%)Pass
Context for chat16K or more20KPass
Writing speed15 tok/s or more15 tok/sPass
First replyunder 3 s, 2K prompt9.9 sFails

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 0528 Qwen3 8B
Parameters
8.2B
Precision
6-bit (Q6_K)
Context
20K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M4 16 GB
GPU can use
10.7 GB of 16.0 GB

Worth trying

  • 8-bit cache: Room for 40K context

Running cost

At home
$0.85/mo
39 W at the wall
Renting instead
$29/mo
RTX 2000 Ada at $0.24/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/DeepSeek-R1-0528-Qwen3-8B-GGUF
vLLM
vllm serve deepseek-ai/DeepSeek-R1-0528-Qwen3-8B
MLX (Mac)
mlx_lm.chat --model mlx-community/DeepSeek-R1-0528-Qwen3-8B-4bit

DeepSeek R1 0528 Qwen3 8B on similar machines

All machines: DeepSeek R1 0528 Qwen3 8B VRAM requirements. Everything that runs here: what can the Mac mini M4 16 GB run?

Other models that run on Mac mini M4 16 GB

Questions

Can DeepSeek R1 0528 Qwen3 8B run on Mac mini M4 16 GB?

DeepSeek R1 0528 Qwen3 8B at 6-bit runs on the M4 16 GB with 20K of context at about 15 tokens a second.

Report VR-0TXQU86, calculated Nov 22, 2026 from published specs, not benchmarked.