Google

Gemma 4 26B A4B IT

CTX262K

61Quality

Reasoning · Vision · Tools

Downloads10M/mo

Likes1.7K

Open Gemma instruction model for efficient chat and self-hosted deployments

Open weightsApache 2.0851/1044

Drag to turn

GoogleTextPromo

Gemma 4 26B A4B IT

Open Gemma instruction model for efficient chat and self-hosted deployments

gemma-4-26b-a4b-it

Type: Text
Quality: 61 · Top 39% on the Epoch Capabilities Index
Context window: 262,144 tokens
Max output: 32,768 tokens
Input price: —
Output price: —
Cache read: —
Cache write: —
Parameters: 26B (25,805,936,206)
Downloads: 10M in the last 30 days
Likes: 1.7K
Access to weights: Open download
Released: Apr 2, 2026
Knowledge cutoff: —
Takes in: Text, Image
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
File attachments: Yes
Access: Open weights
License: Apache 2.0
Rarity: Promo
Set number: 851/1044

Open Google docs Weights on Hugging Face Quality 61 Where to run it 30 Evolution 4/4 Race it 116 tok/s Meet its creature Battle Qwen3 8B

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: ai.google.dev.

How good is it?

Public leaderboard scores for Gemma 4 26B A4B IT, refreshed daily from Epoch AI and LMArena.

Top 39% of the 277 models on the Epoch Capabilities Index: #110.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#110 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.141.8 index
Listed as Gemma 4 26B A4B
LMArena Text#90 of 416
People compare two anonymous answers and vote for the better one.1,434 rating
Listed as gemma-4-26b-a4b
LMArena Text · Coding#107 of 411
The text arena’s coding prompts only.1,446 rating
Listed as gemma-4-26b-a4b
LMArena Text · Math#47 of 400
The text arena’s math prompts only.1,470 rating
Listed as gemma-4-26b-a4b
LMArena Text · Creative writing#96 of 414
The text arena’s creative writing prompts only.1,401 rating
Listed as gemma-4-26b-a4b
LMArena WebDev#110 of 145
Each model builds a web app from the same prompt; people pick the better one.1,360 rating
Listed as Gemma 4 26B A4B
LMArena Vision#55 of 165
Questions about images, voted by people.1,260 rating
Listed as gemma-4-26b-a4b

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

26 providers sell Gemma 4 26B A4B IT through an API, and 4 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestKilo Gateway$0.042 in · $0.22 out
Free to try2 providersNaN, OpenRouter
From the labGoogle— in · — out
Fastest on Hugging FaceScaleway116 tokens/s

API providers

Provider	Input	Output	Context
NaNFree`gemma4`	Free	Free	262K
OpenRouterFree`google/gemma-4-26b-a4b-it:free`	Free	Free	262K
Kilo GatewayCheapest paid`google/gemma-4-26b-a4b-it`	$0.042	$0.22	262K
EmpirioLabs AI`gemma-4-26b-a4b`	$0.05	$0.29	262K
NanoGPT`google/gemma-4-26b-a4b-it`	$0.09	$0.30	262K
Cloudflare Workers AI`@cf/google/gemma-4-26b-a4b-it`	$0.10	$0.30	256K
CoreWeave`google/gemma-4-26B-A4B-it`	$0.10	$0.30	262K
OrcaRouter`google/gemma-4-26b-a4b-it`	$0.06	$0.33	262K
Charm Hyper`gemma-4-26b-a4b-it`	$0.098	$0.33	256K
Deep Infra`google/gemma-4-26B-A4B-it`	$0.07	$0.34	262K

Show 16 more providers

Provider	Input	Output	Context
DevPass (LLM Gateway)`gemma-4-26b-a4b-it`	$0.07	$0.34	262K
LLM Gateway`deepinfra/gemma-4-26b-a4b-it`	$0.07	$0.34	262K
Requesty`gemma-4-26b-a4b-it`	$0.07	$0.34	262K
SiliconFlow`google/gemma-4-26B-A4B-it`	$0.12	$0.40	262K
Amazon Bedrock`google.gemma-4-26b-a4b`	$0.13	$0.40	262K
Merge Gateway`google/gemma-4-26b-a4b-it`	$0.13	$0.40	262K
Novita AI`google/gemma-4-26b-a4b-it`	$0.13	$0.40	262K
AKI.IO`gemma4-26b`	$0.10	$0.50	256K
Scaleway`gemma-4-26b-a4b-it`	$0.25	$0.50	256K
Cortecs`gemma-4-26b-a4b-it`	$0.11	$0.56	262K
evroc`google/gemma-4-26B-A4B-it`	$0.14	$0.57	262K
Vercel AI Gateway`google/gemma-4-26b-a4b-it`	$0.15	$0.60	262K
Vertex`google/gemma-4-26b-a4b-it-maas`	$0.15	$0.60	262K
AI/ML API`google/gemma-4-26b-a4b-it`	$0.21	$0.83	262K
GoogleOfficial`gemma-4-26b-a4b-it`	—	—	262K
Tempr Gateway`google/gemma-4-26b-a4b-it`	—	—	262K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.07	$0.34	262K	80 tok/s	0.4s
NovitaTools	$0.13	$0.40	262K	15 tok/s	1.4s
ScalewayFastestTools	$0.28	$0.57	—	116 tok/s	0.5s
Featherless	—	—	—	—	—

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Gemma 4 26B A4B IT

Gemma 4 26B A4B IT

How good is it?

Leaderboards

Benchmarks Epoch AI runs

Where to run it

API providers

Hugging Face Inference Providers

More from Google

Gemini 4 Argon

embeddinggemma-2

Gemini 3.8 Flash

timesfm-3.0-pytorch

Gemini 3.7 Flash

Gemini 3.6 Flash

Gemini 3.5 Flash Lite

Nano Banana 2 Lite