gemma-4-31B-it vs llava-onevision-qwen2-0.5b-ov-hf
Specs, VRAM requirements and download trends — updated 28 July 2026.
llava-hf · B
Params
890 M
Context
—
30d
1.1 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gemma-4-31B-it | llava-onevision-qwen2-0.5b-ov-hf |
|---|---|---|
| Parameters | 32.7 B | 890 M |
| Architecture | Gemma4ForConditionalGeneration | LlavaOnevisionForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 11,885,389 | 1,050,523 |
| Downloads all time | 45.2 M | 12.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-03-11 | 2024-08-13 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
12.4 M1.0 M
gemma-4-31B-it
llava-onevision-qwen2-0.5b-ov-hf
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
llava-onevision-qwen2-0.5b-ov-hf · fp16
2.6 GB / 24 GB
gemma-4-31B-it · fp16
74.2 GB / 24 GB