Skip to content

Mistral Medium 3.5 128B on M5 Ultra 512 GB: VRAM, speed and fit

Mistral Medium 3.5 128B at FP8 runs on the M5 Ultra 512 GB with 256K of context at about 5.7 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Ultra 512 GB · FP8 · Ollama / LM Studio · Chat

GPU memory
341 GB
of 512 GB
Context
256K
auto
Speed
5.7 tok/s
3.4 when full
First reply
7.6 s
2K prompt

Where the memory goes

Model
124 GB
Context
88.0 GB
Overhead
896 MB
OS
128 GB
Free
171 GB
Memory
341 GB of 512 GB
Context
256K tokens · auto
Speed
5.7 tok/s · 3.4 when full
First reply
7.6 s for a 2K prompt
Running cost
$5.06/mo at home · $574/mo on a cloud 8× A40

Validation: Not validated

What Mistral Medium 3.5 128B on M5 Ultra 512 GB was checked against
CheckTargetResultStatus
Fits in GPU memory384 GB usable213 GB neededPass
Headroom5% free171 GB free (44%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more5.7 tok/sFails
First replyunder 3 s, 2K prompt7.6 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
Mistral Medium 3.5 128B
Parameters
128B
Precision
FP8
Context
256K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
M5 Ultra 512 GB
GPU can use
384 GB of 512 GB

Running cost

At home
$5.06/mo
231 W at the wall
Renting instead
$574/mo
8× A40 at $4.72/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

Ollama
ollama run mistral-medium-3.5:128b
llama.cpp
llama-server -hf unsloth/Mistral-Medium-3.5-128B-GGUF
vLLM
vllm serve mistralai/Mistral-Medium-3.5-128B
MLX (Mac)
mlx_lm.chat --model mlx-community/Mistral-Medium-3.5-128B-4bit

Mistral Medium 3.5 128B on similar machines

All machines: Mistral Medium 3.5 128B VRAM requirements. Everything that runs here: what can the M5 Ultra 512 GB run?

Other models that run on M5 Ultra 512 GB

Questions

Can Mistral Medium 3.5 128B run on M5 Ultra 512 GB?

Mistral Medium 3.5 128B at FP8 runs on the M5 Ultra 512 GB with 256K of context at about 5.7 tokens a second.

Report VR-07DVEN6, calculated Nov 22, 2026 from published specs, not benchmarked.