Skip to content

Qwen3 VL 32B Instruct on M5 Max 128 GB: VRAM, speed and fit

Qwen3 VL 32B Instruct at 8-bit runs on the M5 Max 128 GB with 224K of context at about 12 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
122 GB
of 128 GB
Context
224K
auto
Speed
12 tok/s
4.7 when full
First reply
3.2 s
2K prompt

Where the memory goes

Model
33.0 GB
Context
56.0 GB
Overhead
713 MB
OS
32.0 GB
Free
6.3 GB
Memory
122 GB of 128 GB
Context
224K tokens · auto
Speed
12 tok/s · 4.7 when full
First reply
3.2 s for a 2K prompt
Running cost
$2.63/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Validated with conditions

What Qwen3 VL 32B Instruct on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable89.7 GB neededPass
Headroom5% free6.3 GB free (7%)Pass
Context for chat16K or more224KPass
Writing speed15 tok/s or more12 tok/sCheck
First replyunder 3 s, 2K prompt3.2 sCheck

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 VL 32B Instruct
Parameters
33.4B
Precision
8-bit (Q8_0)
Context
224K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Max 128 GB
GPU can use
96.0 GB of 128 GB

Running cost

At home
$2.63/mo
120 W at the wall
Renting instead
$131/mo
4× RTX A5000 at $1.08/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 Qwen/Qwen3-VL-32B-Instruct-GGUF
vLLM
vllm serve Qwen/Qwen3-VL-32B-Instruct

Qwen3 VL 32B Instruct on similar machines

All machines: Qwen3 VL 32B Instruct VRAM requirements. Everything that runs here: what can the M5 Max 128 GB run?

Other models that run on M5 Max 128 GB

Questions

Can Qwen3 VL 32B Instruct run on M5 Max 128 GB?

Qwen3 VL 32B Instruct at 8-bit runs on the M5 Max 128 GB with 224K of context at about 12 tokens a second.

Report VR-1W0L77H, calculated Nov 22, 2026 from published specs, not benchmarked.