Skip to content

Qwen3 Coder 30B A3B Instruct on M3 Ultra 96 GB: VRAM, speed and fit

Qwen3 Coder 30B A3B Instruct at 8-bit runs on the M3 Ultra 96 GB with 256K of context at about 79 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
78.8 GB
of 96.0 GB
Context
256K
auto
Speed
79 tok/s
16 when full
First reply
1.7 s
2K prompt

Where the memory goes

Model
30.2 GB
Context
24.0 GB
Overhead
617 MB
OS
24.0 GB
Free
17.2 GB
Memory
78.8 GB of 96.0 GB
Context
256K tokens · auto
Speed
79 tok/s · 16 when full
First reply
1.7 s for a 2K prompt
Running cost
$3.55/mo at home · $117/mo on a cloud 4× RTX 2000 Ada

Validation: Validated

What Qwen3 Coder 30B A3B Instruct on M3 Ultra 96 GB was checked against
CheckTargetResultStatus
Fits in GPU memory72.0 GB usable54.8 GB neededPass
Headroom5% free17.2 GB free (24%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more79 tok/sPass
First replyunder 3 s, 2K prompt1.7 sPass

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 Coder 30B A3B Instruct
Parameters
30.5B, 3B active
Precision
8-bit (Q8_0)
Context
256K, 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
$117/mo
4× RTX 2000 Ada at $0.96/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/Qwen3-Coder-30B-A3B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen3-Coder-30B-A3B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen3-Coder-30B-A3B-Instruct-4bit

Qwen3 Coder 30B A3B Instruct on similar machines

All machines: Qwen3 Coder 30B A3B 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 Qwen3 Coder 30B A3B Instruct run on M3 Ultra 96 GB?

Qwen3 Coder 30B A3B Instruct at 8-bit runs on the M3 Ultra 96 GB with 256K of context at about 79 tokens a second.

Report VR-0IAFZJ2, calculated Nov 22, 2026 from published specs, not benchmarked.