Gemma-4-31B-IT-NVFP4 vs DeepSeek-R1-Distill-Qwen-14B
Specs, VRAM requirements and download trends — updated 28 August 2026.
deepseek-ai · B · Open weights
Params
14.8 B
Context
131,072
30d
190 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Gemma-4-31B-IT-NVFP4 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| Parameters | 20.9 B | 14.8 B |
| Architecture | Gemma4ForConditionalGeneration | Qwen2ForCausalLM |
| Context length | — | 131,072 |
| Licence | other | mit |
| Commercial use | Unknown | Allowed |
| Languages | — | — |
| Downloads 30d | 1,136,331 | 189,567 |
| Downloads all time | 14.3 M | 9.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-02 | 2025-01-20 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.4 M190 K
Gemma-4-31B-IT-NVFP4
DeepSeek-R1-Distill-Qwen-14B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Gemma-4-31B-IT-NVFP4 · fp16
39.5 GB / 24 GB
DeepSeek-R1-Distill-Qwen-14B · fp16 @ 128K ctx
68.4 GB / 24 GB