gemma-4-31B-it vs Qwen2.5-VL-72B-Instruct
Specs, VRAM requirements and download trends — updated 24 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-31B-it | Qwen2.5-VL-72B-Instruct |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 32.7 B | 73.4 B |
| Architecture | Gemma4ForConditionalGeneration | Qwen2_5_VLForConditionalGeneration |
| Context length | 262,144 | 128,000 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 8,540,107 | 89,270 |
| Downloads all time | 69.2 M | 7.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-03-11 | 2025-01-27 |
| API input price / 1M tokens | $0.20 | $0.80 |
| API output price / 1M tokens | $0.40 | $1.00 |
| Est. cost per 1M input + 1M output tokens | $0.60 | $1.80 |
| Cached input / 1M tokens | — | $0.40 |
| AA Intelligence Index | 14.7 | — |
| AA Coding Index | 43.4 | — |
| AA Agentic Index | 4.2 | — |
| Max output tokens | 16,384 | 115,200 |
| API providers | 12 | 1 |
| Tool calling | Yes | No |
| Reasoning mode | Yes | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gemma-4-31B-it
$0.60
Qwen2.5-VL-72B-Instruct
$1.80
gemma-4-31B-it is 3.0× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
12.4 M59 K
gemma-4-31B-it
Qwen2.5-VL-72B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-4-31B-it · fp16
74.2 GB / 24 GB
Qwen2.5-VL-72B-Instruct · fp16 @ 125K ctx
334.1 GB / 24 GB