gemma-4-31B-it vs Qwen3-VL-30B-A3B-Instruct-FP8
Specs, VRAM requirements and download trends — updated 30 August 2026.
Qwen · B · Open weights
Params
31.1 B
Context
—
30d
801 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-31B-it | Qwen3-VL-30B-A3B-Instruct-FP8 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 32.7 B | 31.1 B |
| Architecture | Gemma4ForConditionalGeneration | Qwen3VLMoeForConditionalGeneration |
| Context length | 262,144 | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 7,079,469 | 800,693 |
| Downloads all time | 73.4 M | 3.9 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-03-11 | 2025-10-01 |
| API input price / 1M tokens | $0.20 | not on OpenRouter |
| API output price / 1M tokens | $0.40 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.60 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | 4.4 | not on OpenRouter |
| AA Coding Index | 43.4 | not on OpenRouter |
| AA Agentic Index | 4.2 | not on OpenRouter |
| Max output tokens | 16,384 | not on OpenRouter |
| API providers | 16 | 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-4-31B-it
$0.60
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
10.0 M801 K
gemma-4-31B-it
Qwen3-VL-30B-A3B-Instruct-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-30B-A3B-Instruct-FP8 · fp16
40.6 GB / 24 GB
gemma-4-31B-it · fp16
74.2 GB / 24 GB