Google logo

DiffusionGemma 26B A4B

Pricing & Specs API
Free REST API for prices, specs and benchmarks
DiffusionGemma 26B A4B is Google's language model. A diffusion-based language model built on the Gemma architecture, designed for text generation using a masked diffusion approach rather than autoregressive decoding.
Specifications
Canonical IDgoogle-diffusiongemma-26b-a4b
TypeLanguage
StatusActive
CreatorGoogleGoogle
Input ModalitiesText
Output ModalitiesText
Parameters26B
Benchmarks
Intelligence Index
13.5
#253
Coding Index
19.7
#115
GPQA
0.7
#238
HLE
0.1
#158
IFBench
0.6
#110
Time to First Token
0.00s
#137
SciCode
0.3
#208
LCR
0.1
#300
Output TPS
0.0
#257

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Cheapest Instances to Run It

Cloud GPU instances that can host DiffusionGemma 26B A4B, ranked by cheapest on-demand price. The model needs about 62 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
Standard_NP10sAzureAMD Alveo U250 FPGA (64GB)64 GB$1.65/hrwestus2
Standard_NV32as_v4AzureAMD Radeon Instinct MI2564 GB$1.86/hrwestus2
Standard_NP20sAzure2× AMD Alveo U250 FPGA (64GB)128 GB$3.30/hrwestus2
7 more instances can run DiffusionGemma 26B A4B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Model IDs

diffusiongemma-26b-a4b
google-diffusiongemma-26b-a4b