Qwen2.5-7B-Instruct-AWQ vs Gemma-4-E4B-DECKARD-HERETIC-NVFP4
Specs, VRAM requirements and download trends — updated 21 September 2026.
AEON-7 · B
Params
6.2 B
Context
—
30d
216 K
gemma licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-7B-Instruct-AWQ | Gemma-4-E4B-DECKARD-HERETIC-NVFP4 |
|---|---|---|
| Parameters | 7.6 B | 6.2 B |
| Architecture | Qwen2ForCausalLM | Gemma4ForConditionalGeneration |
| Context length | 32,768 | — |
| Licence | apache-2.0 | gemma |
| Commercial use | Allowed | Conditional |
| Languages | 1 | 1 |
| Downloads 30d | 3,504,235 | 215,526 |
| Downloads all time | 22.9 M | 249 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-04-13 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
4.7 M216 K
Qwen2.5-7B-Instruct-AWQ
Gemma-4-E4B-DECKARD-HERETIC-NVFP4
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-7B-Instruct-AWQ · fp16
7.8 GB / 24 GB
Gemma-4-E4B-DECKARD-HERETIC-NVFP4 · fp16
12.6 GB / 24 GB