Skip to content

Mistral Medium 3.5 128B on H100 SXM: VRAM, speed and fit

Mistral Medium 3.5 128B at 3-bit runs on the H100 SXM with 48K of context at about 35 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on H100 SXM · 3-bit (Q3_K_M) · Ollama / LM Studio · Chat

GPU memory
75.7 GB
of 80.0 GB
Context
48K
auto
Speed
35 tok/s
27 when full
First reply
1.7 s
2K prompt

Where the memory goes

Model
58.1 GB
Context
16.5 GB
Overhead
1.1 GB
OS
0.0 GB
Free
4.3 GB
Memory
75.7 GB of 80.0 GB
Context
48K tokens · auto
Speed
35 tok/s · 27 when full
First reply
1.7 s for a 2K prompt
Running cost
$11/mo at home · $122/mo on a cloud 4× RTX A4500

Validation: Validated

What Mistral Medium 3.5 128B on H100 SXM was checked against
CheckTargetResultStatus
Fits in GPU memory80.0 GB usable75.7 GB neededPass
Headroom5% free4.3 GB free (5%)Pass
Context for chat16K or more48KPass
Writing speed15 tok/s or more35 tok/sPass
First replyunder 3 s, 2K prompt1.7 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
Mistral Medium 3.5 128B
Parameters
128B
Precision
3-bit (Q3_K_M)
Context
48K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
H100 SXM
GPU can use
80.0 GB of 80.0 GB

Worth trying

  • 8-bit cache: Room for 88K context

Running cost

At home
$11/mo
500 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 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 H100 SXM run?

Other models that run on H100 SXM

Questions

Can Mistral Medium 3.5 128B run on H100 SXM?

Mistral Medium 3.5 128B at 3-bit runs on the H100 SXM with 48K of context at about 35 tokens a second.

Report VR-1KR9R1R, calculated Nov 22, 2026 from published specs, not benchmarked.