Qwen3-8B vs Gemma-4-E4B-DECKARD-HERETIC-NVFP4

Specs, VRAM requirements and download trends — updated 6 August 2026.

Qwen · A
Params
8.2 B
Context
40,960
30d
16.3 M
apache-2.0 · commercial OK
AEON-7 · B
Params
6.2 B
Context
30d
217 K
gemma licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3-8B Gemma-4-E4B-DECKARD-HERETIC-NVFP4
Parameters 8.2 B 6.2 B
Architecture Qwen3ForCausalLM Gemma4ForConditionalGeneration
Context length 40,960
Licence apache-2.0 gemma
Commercial use Allowed Conditional
Languages 1
Downloads 30d 16,272,885 217,459
Downloads all time 103.2 M 249 K
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2025-04-27 2026-04-13

Download trend

Daily snapshots, last 10 days (28 Jul – 6 Aug)

16.6 M217 K
Qwen3-8B Gemma-4-E4B-DECKARD-HERETIC-NVFP4

VRAM side by side

On RTX 4090 · 24 GB · 8K context unless noted

Gemma-4-E4B-DECKARD-HERETIC-NVFP4 · fp16 12.6 GB / 24 GB
✅ Runs comfortably
Qwen3-8B · fp16 19.7 GB / 24 GB
⚠️ Tight — reduce context

Adjacent comparisons