gemma-4-26B-A4B-it vs Qwen2.5-VL-7B-Instruct
Specs, VRAM requirements and download trends — updated 23 October 2026.
google · A · Open weights
Params
26.5 B
Context
—
30d
9.4 M
apache-2.0 · commercial OK
Qwen · B · Open weights
Params
8.3 B
Context
128,000
30d
5.0 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-26B-A4B-it | Qwen2.5-VL-7B-Instruct |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 26.5 B | 8.3 B |
| Architecture | Gemma4ForConditionalGeneration | Qwen2_5_VLForConditionalGeneration |
| Context length | 262,144 | 128,000 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 9,441,586 | 5,033,876 |
| Downloads all time | 72.3 M | 106.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-03-11 | 2025-01-26 |
| API input price / 1M tokens | $0.077 | not on OpenRouter |
| API output price / 1M tokens | $0.26 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.33 | not on OpenRouter |
| Cached input / 1M tokens | $0.043 | not on OpenRouter |
| AA Intelligence Index | 16.7 | not on OpenRouter |
| AA Coding Index | 39.3 | not on OpenRouter |
| AA Agentic Index | 2.9 | not on OpenRouter |
| Max output tokens | 235,929 | not on OpenRouter |
| API providers | 13 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gemma-4-26B-A4B-it
$0.33
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
13.1 M5.0 M
gemma-4-26B-A4B-it
Qwen2.5-VL-7B-Instruct
A overtook B on 1 Sep
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-VL-7B-Instruct · fp16 @ 125K ctx
38.2 GB / 24 GB
gemma-4-26B-A4B-it · fp16
61.3 GB / 24 GB