gemma-4-31B-it vs Llama-Guard-4-12B
Specs, VRAM requirements and download trends — updated 24 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-31B-it | Llama-Guard-4-12B |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 32.7 B | 12.0 B |
| Architecture | Gemma4ForConditionalGeneration | Llama4ForConditionalGeneration |
| Context length | 262,144 | 163,840 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 1 |
| Downloads 30d | 8,540,107 | 44,083 |
| Downloads all time | 69.2 M | 1.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2026-03-11 | 2025-04-23 |
| API input price / 1M tokens | $0.20 | $0.18 |
| API output price / 1M tokens | $0.40 | $0.18 |
| Est. cost per 1M input + 1M output tokens | $0.60 | $0.36 |
| Cached input / 1M tokens | — | — |
| AA Intelligence Index | 14.7 | — |
| AA Coding Index | 43.4 | — |
| AA Agentic Index | 4.2 | — |
| Max output tokens | 16,384 | 16,384 |
| 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
Llama-Guard-4-12B
$0.36
Llama-Guard-4-12B is 1.7× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
12.4 M46 K
gemma-4-31B-it
Llama-Guard-4-12B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-Guard-4-12B · fp16
28.7 GB / 24 GB
gemma-4-31B-it · fp16
74.2 GB / 24 GB