gemma-4-26B-A4B-it
Hugging Face GitHub Launch Blog Documentation Technical Report License: Apache 2.0 Authors: Google DeepMind
Params
26.5 B
Context
—
Downloads 30d
5.5 M
Likes
1,750
Download history
daily snapshots · 106 days
▲ 6.3 M in the last 30 days (53.5%)
11.7 M5.5 M
Oct 12Oct 22Nov 1Nov 10
13.1 M5.5 M
Aug 13Sep 12Oct 12Nov 10
13.1 M5.5 M
Jul 28Sep 1Oct 6Nov 10
Can you run it?
Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.
| File | Quant | Size | Est. VRAM | Verdict on RTX 4090 · 24 GB |
|---|---|---|---|---|
| model.safetensors | bf16 | 51.6 GB | 61.3 GB | ❌ Won’t fit |
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.
Use via API
via OpenRouter · USD per 1M tokens · synced 2026-11-10$0.08
input / 1M
$0.10
output / 1M
$0.046
cached input / 1M
$0.18
1M in + 1M out
:free variant
Free in · Free out
- Context window
- 256,000 tokens
- Max output
- 128,000 tokens
- Providers
- 15
- Cheapest provider
- PrimeIntellect · $0.031 / $0.092
- Best throughput
- —
- AA Intelligence / Coding / Agentic
- — / 39.3 / 2.9
✓ Tool calling
✓ Reasoning
✓ Structured outputs
✓ Image input
✗ File input
✗ Audio input
✓ Prompt caching
Specifications
- Architecture
- Gemma4ForConditionalGeneration
- Parameters
- 26.5 B
- Tensor type
- BF16
- Licence
- apache-2.0
- First seen on the Hub
- 2026-03-11
- Base model
- gemma-4-26B-A4B
- Training datasets
- undisclosed
- Added to our catalog
- 2026-07-28
Family
Base model and the most-downloaded derivatives in the catalog.
Base
gemma-4-26B-A4B google
865 K
Derivative
OTel-2.0-Decision-26B-A4B-4bit farbodtavakkoli
3.2 M
Derivative
gemma-4-26B-A4B-it-GGUF unsloth
2.0 M
Derivative
Gemma-4-26B-A4B-NVFP4 nvidia
1.7 M
Derivative
gemma-4-26B-A4B-it-FP8-dynamic RedHatAI
1.3 M
Derivative
gemma-4-26B-A4B-it-AWQ-4bit cyankiwi
1.1 M
Compare with any image-text-to-text model