gemma-4-26B-A4B-it vs Llama-4-Scout-17B-16E-Instruct
Specs, VRAM requirements and download trends — updated 24 October 2026.
google · A · Open weights
Params
26.5 B
Context
—
30d
9.1 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-26B-A4B-it | Llama-4-Scout-17B-16E-Instruct |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 26.5 B | 108.6 B |
| Architecture | Gemma4ForConditionalGeneration | Llama4ForConditionalGeneration |
| Context length | 262,144 | 327,680 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 12 |
| Downloads 30d | 9,095,856 | 144,941 |
| Downloads all time | 72.4 M | 7.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2026-03-11 | 2025-04-02 |
| API input price / 1M tokens | $0.068 | $0.10 |
| API output price / 1M tokens | $0.23 | $0.30 |
| Est. cost per 1M input + 1M output tokens | $0.29 | $0.40 |
| Cached input / 1M tokens | $0.038 | — |
| AA Intelligence Index | 16.7 | 6.5 |
| AA Coding Index | 39.3 | 8.2 |
| AA Agentic Index | 2.9 | 0.5 |
| Max output tokens | 235,929 | 16,384 |
| API providers | 13 | 2 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gemma-4-26B-A4B-it
$0.29
Llama-4-Scout-17B-16E-Instruct
$0.40
gemma-4-26B-A4B-it is 1.4× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
13.1 M148 K
gemma-4-26B-A4B-it
Llama-4-Scout-17B-16E-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-4-26B-A4B-it · fp16
61.3 GB / 24 GB
Llama-4-Scout-17B-16E-Instruct · fp16
255.8 GB / 24 GB