Qwen3-4B-Instruct-2507 vs t5gemma-2b-2b-ul2-it
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · A · Open weights
Params
4.0 B
Context
262,144
30d
2.6 M
apache-2.0 · commercial OK
google · B · Open weights
Params
5.6 B
Context
—
30d
173 K
gemma licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-4B-Instruct-2507 | t5gemma-2b-2b-ul2-it |
|---|---|---|
| Parameters | 4.0 B | 5.6 B |
| Architecture | Qwen3ForCausalLM | T5GemmaForConditionalGeneration |
| Context length | 262,144 | — |
| Licence | apache-2.0 | gemma |
| Commercial use | Allowed | Conditional |
| Languages | — | — |
| Downloads 30d | 2,557,680 | 172,926 |
| Downloads all time | 66.6 M | 328 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2025-08-05 | 2025-06-19 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.0 M143 K
Qwen3-4B-Instruct-2507
t5gemma-2b-2b-ul2-it
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
t5gemma-2b-2b-ul2-it · fp16
13.7 GB / 24 GB
Qwen3-4B-Instruct-2507 · fp16 @ 256K ctx
28.6 GB / 24 GB