Gemma 4 26B A4B
googleapache-2.0textvision

Gemma 4 26B A4B

Updated Jun 7, 2026
Parameters
26.5B
Context
262,144
License
apache-2.0
Updated
Jun 7, 2026

Intelligence benchmarks

Artificial Analysis indexes - compared with the best open and proprietary models

Intelligence

31.2

AA Index

Coding

22.4

AA Index

Agentic

32.1

AA Index

Intelligence Index - Gemma 4 26B A4B vs. the field

Best open-weight models (you can run locally) and leading proprietary models for context.

Claude Opus 4.8 (max)
61.4
closed
GPT-5.5 (xhigh)
60.2
closed
Claude Opus 4.7 (max)
57.3
closed
Gemini 3.1 Pro Preview
57.2
closed
Qwen3.7 Max
56.6
closed
Kimi K2.6
53.9
open
MiMo-V2.5-Pro
53.8
open
Gemma 4 26B A4B
31.2
open

Coding Index comparison

GPT-5.5 (xhigh)
59.1
closed
Claude Opus 4.8 (max)
56.7
closed
Gemini 3.1 Pro Preview
55.5
closed
Claude Opus 4.7 (Non-reasoning, high)
53.1
closed
GPT-5.3 Codex (xhigh)
53.1
closed
DeepSeek V4 Pro (Max)
47.5
open
Kimi K2.6
47.1
open
Gemma 4 26B A4B
22.4
open

Agentic Index comparison

Claude Opus 4.8 (max)
77.8
closed
GPT-5.5 (xhigh)
74.1
closed
Claude Opus 4.7 (max)
71.3
closed
Gemini 3.5 Flash (medium)
70.4
closed
MiniMax-M3
68.6
closed
MiMo-V2.5-Pro
67.4
open
DeepSeek V4 Pro (Max)
67.2
open
Gemma 4 26B A4B
32.1
open

Benchmark data from Artificial Analysis · updated 2026-06-07.

Standard benchmarks

Performance across standard evaluations

BenchmarkScore
GPQA79.2

Will it run on your hardware?

Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest

Runs on your 24 GB - best at Q5_K_M
2 of 4 quantizations fit Gemma 4 26B A4B with real runtime overhead.
Q4_K_M
15 GB
Q5_K_M
19 GB
fits tight too big

Need an exact figure for your context length? Use the VRAM calculator.

Run it locally

Copy-paste - running in under a minute

vLLMOpenAI-compatible API
vllm serve google/gemma-4-26B-A4B-it

New to this? Start with Ollama · serve to many users with vLLM.

Deep dive

Notes, sources, and the full write-up

Gemma 4 26B A4B is a 26.5B-parameter apache-2.0 model from Google. It scores 31.2 on the Artificial Analysis Intelligence Index (coding 22.4). At Q4_K_M it needs roughly 15 GB of VRAM, placing it in the 12–24 GB GPU hardware tier.

Benchmarks

Artificial Analysis Intelligence Index - Gemma 4 26B A4B vs. leading closed models:

ModelIntelligenceCodingGPQA
Gemma 4 26B A4B31.222.479.2
GPT-5.5 (xhigh)60.259.193.5
Claude Opus 4.8 (max)61.456.792
Gemini 3.1 Pro Preview57.255.594.1
Grok 4.3 (high)53.24190.1

Source: Artificial Analysis (2026-06-07).

Popularity

Gemma 4 26B A4B has 12,161,679 downloads in the last month on HuggingFace and 1,096 likes.

Frequently asked

Quick answers to common questions

How much VRAM does Gemma 4 26B A4B need?

Gemma 4 26B A4B with 26.5B parameters needs approximately 15 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.

Is Gemma 4 26B A4B better than other google models?

Gemma 4 26B A4B has 26.5B parameters with 262,144 context - a strong choice for general use.

What license is Gemma 4 26B A4B under?

Gemma 4 26B A4B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.

What hardware runs Gemma 4 26B A4B well?

With 26.5B parameters, Gemma 4 26B A4B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.

What is the best quantization for Gemma 4 26B A4B?

Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~19 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.

How long can Gemma 4 26B A4B's context window handle?

Gemma 4 26B A4B supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.

What models compete with Gemma 4 26B A4B?

Gemma 4 26B A4B competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.

Nearby options

Similar models and compatible hardware by spec

Comments coming soon

Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.