gemma-4-31B-it vs Qwen3.8-Flash-Next
Specs, VRAM requirements and download trends — updated 23 October 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-31B-it | Qwen3.8-Flash-Next |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 32.7 B | 180.0 B |
| Architecture | Gemma4ForConditionalGeneration | Qwen4ExpForConditionalGeneration |
| Context length | 262,144 | 1,000,000 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 8,630,477 | 2,706,809 |
| Downloads all time | 69.0 M | 3.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-03-11 | 2026-08-24 |
| API input price / 1M tokens | $0.20 | $0.15 |
| API output price / 1M tokens | $0.40 | $0.47 |
| Est. cost per 1M input + 1M output tokens | $0.60 | $0.62 |
| Cached input / 1M tokens | — | $0.016 |
| AA Intelligence Index | 14.7 | — |
| AA Coding Index | 43.4 | — |
| AA Agentic Index | 4.2 | — |
| Max output tokens | 16,384 | 131,072 |
| API providers | 12 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gemma-4-31B-it
$0.60
Qwen3.8-Flash-Next
$0.62
gemma-4-31B-it is 1.0× cheaper at list price.
Download trend
Daily snapshots, last 88 days (28 Jul – 23 Oct)
12.4 M830 K
gemma-4-31B-it
Qwen3.8-Flash-Next
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gemma-4-31B-it · fp16
74.2 GB / 24 GB
Qwen3.8-Flash-Next · fp16
423.5 GB / 24 GB