Skip to content

Diffusiongemma 26B A4B IT on RTX 5090: VRAM, speed and fit

Diffusiongemma 26B A4B IT at 8-bit runs on the RTX 5090 with 184K of context at about 193 tokens a second.

Text generation · Chat · Ollama / LM Studio

Runs comfortably · on RTX 5090 · 8-bit (Q8_0) · Ollama / LM Studio · Chat

GPU memory
30.4 GB
of 32.0 GB
Context
184K
auto
Speed
193 tok/s
119 when full
First reply
0.2 s
2K prompt

Where the memory goes

Model
25.6 GB
Context
3.8 GB
Overhead
1.0 GB
OS
0.0 GB
Free
1.6 GB
Memory
30.4 GB of 32.0 GB
Context
184K tokens · auto
Speed
193 tok/s · 119 when full
First reply
0.2 s for a 2K prompt
Running cost
$9.30/mo at home · $58/mo on a cloud 2× RTX 2000 Ada

Validation: Validated

What Diffusiongemma 26B A4B IT on RTX 5090 was checked against
CheckTargetResultStatus
Fits in GPU memory32.0 GB usable30.4 GB neededPass
Headroom5% free1.6 GB free (5%)Pass
Context for chat16K or more184KPass
Writing speed15 tok/s or more193 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
184K, auto
Chats at once
1
Use
Chat
Runs in
Ollama / LM Studio
Hardware
RTX 5090
GPU can use
32.0 GB of 32.0 GB

Running cost

At home
$9.30/mo
425 W at the wall
Renting instead
$58/mo
2× RTX 2000 Ada at $0.48/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

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

All machines: Diffusiongemma 26B A4B IT VRAM requirements. Everything that runs here: what can the RTX 5090 run?

Other models that run on RTX 5090

Questions

Can Diffusiongemma 26B A4B IT run on RTX 5090?

Diffusiongemma 26B A4B IT at 8-bit runs on the RTX 5090 with 184K of context at about 193 tokens a second.

Report VR-1L3RR9D, calculated Nov 22, 2026 from published specs, not benchmarked.