Skip to content

Devstral Small 2 24B on M5 Max 128 GB: VRAM, speed and fit

Devstral Small 2 24B at FP8 runs on the M5 Max 128 GB with 384K of context at about 17 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M5 Max 128 GB · FP8 · Ollama / LM Studio · Chat

GPU memory
117 GB
of 128 GB
Context
384K
auto
Speed
17 tok/s
5.1 when full
First reply
2.3 s
2K prompt

Where the memory goes

Model
24.0 GB
Context
60.0 GB
Overhead
672 MB
OS
32.0 GB
Free
11.3 GB
Memory
117 GB of 128 GB
Context
384K tokens · auto
Speed
17 tok/s · 5.1 when full
First reply
2.3 s for a 2K prompt
Running cost
$2.63/mo at home · $131/mo on a cloud 4× RTX A5000

Validation: Validated

What Devstral Small 2 24B on M5 Max 128 GB was checked against
CheckTargetResultStatus
Fits in GPU memory96.0 GB usable84.7 GB neededPass
Headroom5% free11.3 GB free (12%)Pass
Context for chat16K or more384KPass
Writing speed15 tok/s or more17 tok/sPass
First replyunder 3 s, 2K prompt2.3 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
Devstral Small 2 24B
Parameters
24B
Precision
FP8
Context
384K, 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 21, 2026.

How to run it

Ollama
ollama run devstral-small-2:24b
llama.cpp
llama-server -hf unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF
vLLM
vllm serve mistralai/Devstral-Small-2-24B-Instruct-2512
MLX (Mac)
mlx_lm.chat --model mlx-community/Devstral-Small-2-24B-Instruct-2512-4bit

Devstral Small 2 24B on similar machines

All machines: Devstral Small 2 24B 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 Devstral Small 2 24B run on M5 Max 128 GB?

Devstral Small 2 24B at FP8 runs on the M5 Max 128 GB with 384K of context at about 17 tokens a second.

Report VR-04HX2YY, calculated Nov 22, 2026 from published specs, not benchmarked.