Gemma-4-31B-IT-NVFP4 vs Qwen3-Next-80B-A3B-Instruct
Specs, VRAM requirements and download trends — updated 6 August 2026.
Qwen · B · Open weights
Params
81.3 B
Context
262,144
30d
157 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Gemma-4-31B-IT-NVFP4 | Qwen3-Next-80B-A3B-Instruct |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 20.9 B | 81.3 B |
| Architecture | Gemma4ForConditionalGeneration | Qwen3NextForCausalLM |
| Context length | — | 262,144 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 879,282 | 157,094 |
| Downloads all time | 13.5 M | 16.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-02 | 2025-09-09 |
| API input price / 1M tokens | not on OpenRouter | $0.09 |
| API output price / 1M tokens | not on OpenRouter | $1.10 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.19 |
| Cached input / 1M tokens | not on OpenRouter | — |
| AA Intelligence Index | not on OpenRouter | 9.6 |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 16,384 |
| API providers | not on OpenRouter | 3 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-Next-80B-A3B-Instruct
$1.19
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
2.8 M157 K
Gemma-4-31B-IT-NVFP4
Qwen3-Next-80B-A3B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Gemma-4-31B-IT-NVFP4 · fp16
39.5 GB / 24 GB
Qwen3-Next-80B-A3B-Instruct · fp16 @ 256K ctx
569.8 GB / 24 GB