Skip to content

Qwen2.5 Coder 32B Instruct on M3 Ultra 96 GB: VRAM, speed and fit

Qwen2.5 Coder 32B Instruct at 8-bit runs on the M3 Ultra 96 GB with 32K of context at about 15 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
65.1 GB
of 96.0 GB
Context
32K
auto
Speed
15 tok/s
12 when full
First reply
6.1 s
2K prompt

Where the memory goes

Model
32.4 GB
Context
8.0 GB
Overhead
713 MB
OS
24.0 GB
Free
30.9 GB
Memory
65.1 GB of 96.0 GB
Context
32K tokens · auto
Speed
15 tok/s · 12 when full
First reply
6.1 s for a 2K prompt
Running cost
$3.55/mo at home · $66/mo on a cloud 2× RTX A5000

Validation: Not validated

What Qwen2.5 Coder 32B Instruct on M3 Ultra 96 GB was checked against
CheckTargetResultStatus
Fits in GPU memory72.0 GB usable41.1 GB neededPass
Headroom5% free30.9 GB free (43%)Pass
Context for chat16K or more32KPass
Writing speed15 tok/s or more15 tok/sCheck
First replyunder 3 s, 2K prompt6.1 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
Qwen2.5 Coder 32B Instruct
Parameters
32.8B
Precision
8-bit (Q8_0)
Context
32K, 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 21, 2026.

How to run it

llama.cpp
llama-server -hf Qwen/Qwen2.5-Coder-32B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen2.5-Coder-32B-Instruct
MLX (Mac)
mlx_lm.chat --model mlx-community/Qwen2.5-Coder-32B-Instruct-4bit

Qwen2.5 Coder 32B Instruct on similar machines

All machines: Qwen2.5 Coder 32B 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 Qwen2.5 Coder 32B Instruct run on M3 Ultra 96 GB?

Qwen2.5 Coder 32B Instruct at 8-bit runs on the M3 Ultra 96 GB with 32K of context at about 15 tokens a second.

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