Skip to content

Devstral Small 2 24B on M3 Ultra 96 GB: VRAM, speed and fit

Devstral Small 2 24B at FP8 runs on the M3 Ultra 96 GB with 256K of context at about 20 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on M3 Ultra 96 GB · FP8 · Ollama / LM Studio · Chat

GPU memory
88.7 GB
of 96.0 GB
Context
256K
auto
Speed
20 tok/s
7.6 when full
First reply
4.4 s
2K prompt

Where the memory goes

Model
24.0 GB
Context
40.0 GB
Overhead
672 MB
OS
24.0 GB
Free
7.3 GB
Memory
88.7 GB of 96.0 GB
Context
256K tokens · auto
Speed
20 tok/s · 7.6 when full
First reply
4.4 s for a 2K prompt
Running cost
$3.55/mo at home · $122/mo on a cloud 4× RTX A4500

Validation: Validated with conditions

What Devstral Small 2 24B on M3 Ultra 96 GB was checked against
CheckTargetResultStatus
Fits in GPU memory72.0 GB usable64.7 GB neededPass
Headroom5% free7.3 GB free (10%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more20 tok/sPass
First replyunder 3 s, 2K prompt4.4 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
Devstral Small 2 24B
Parameters
24B
Precision
FP8
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
$122/mo
4× RTX A4500 at $1.00/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 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 M3 Ultra 96 GB run?

Other models that run on M3 Ultra 96 GB

Questions

Can Devstral Small 2 24B run on M3 Ultra 96 GB?

Devstral Small 2 24B at FP8 runs on the M3 Ultra 96 GB with 256K of context at about 20 tokens a second.

Report VR-1QB8RL5, calculated Nov 22, 2026 from published specs, not benchmarked.