Skip to content

Diffusiongemma 26B A4B IT on H100 SXM: VRAM, speed and fit

Diffusiongemma 26B A4B IT at 8-bit runs on the H100 SXM with 256K of context at about 277 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on H100 SXM · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
31.8 GB
of 80.0 GB
Context
256K
auto
Speed
277 tok/s
167 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
25.6 GB
Context
5.2 GB
Overhead
1.0 GB
OS
0.0 GB
Free
48.2 GB
Memory
31.8 GB of 80.0 GB
Context
256K tokens · auto
Speed
277 tok/s · 167 when full
First reply
0.2 s for a 2K prompt
Running cost
$11/mo at home · $61/mo on a cloud 2× RTX A4500

Validation: Validated

What Diffusiongemma 26B A4B IT on H100 SXM was checked against
CheckTargetResultStatus
Fits in GPU memory80.0 GB usable31.8 GB neededPass
Headroom5% free48.2 GB free (60%)Pass
Context for chat16K or more256KPass
Writing speed15 tok/s or more277 tok/sPass
First replyunder 3 s, 2K prompt0.2 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
Diffusiongemma 26B A4B IT
Parameters
25.8B, 4B active
Precision
8-bit (Q8_0)
Context
256K, 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

Running cost

At home
$11/mo
500 W at the wall
Renting instead
$61/mo
2× RTX A4500 at $0.50/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 unsloth/diffusiongemma-26B-A4B-it-GGUF
vLLM
vllm serve google/diffusiongemma-26B-A4B-it
MLX (Mac)
mlx_lm.chat --model mlx-community/diffusiongemma-26B-A4B-it-4bit

Diffusiongemma 26B A4B IT on similar machines

  • 2× RTX PRO 6000 BlackwellRuns
  • 4× RTX PRO 6000 BlackwellRuns
  • 8× RTX PRO 6000 BlackwellRuns
  • A100 80 GB SXMRuns
  • 4× H200 NVLRuns
  • 8× H200 NVLRuns

All machines: Diffusiongemma 26B A4B IT VRAM requirements. Everything that runs here: what can the H100 SXM run?

Other models that run on H100 SXM

Questions

Can Diffusiongemma 26B A4B IT run on H100 SXM?

Diffusiongemma 26B A4B IT at 8-bit runs on the H100 SXM with 256K of context at about 277 tokens a second.

Report VR-0LBYTFS, calculated Nov 22, 2026 from published specs, not benchmarked.