Qwen3.5-2B vs Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced

Specs, VRAM requirements and download trends — updated 29 September 2026.

Qwen · A · Open weights
Params
2.3 B
Context
—
30d
2.9 M
apache-2.0 · commercial OK
HauhauCS · B · Open weights
Params
12.0 B
Context
—
30d
832 K
gemma licence · conditional

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.5-2B Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced
Parameters 2.3 B 12.0 B
Architecture Qwen3_5ForConditionalGeneration —
Context length — —
Licence apache-2.0 gemma
Commercial use Allowed Conditional
Languages — 1
Downloads 30d 2,933,129 831,961
Downloads all time 20.1 M 2.1 M
Quantizations on the Hub SAFETENSORS GGUF
Gated No No
First seen on the Hub 2026-02-28 2026-06-22

Download trend

Daily snapshots, last 89 days (28 Jul – 24 Oct)

4.9 M801 K
Qwen3.5-2B Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced

VRAM side by side

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

Qwen3.5-2B · fp16 5.8 GB / 24 GB
✅ Runs comfortably
Gemma4-12B-QAT-Uncensored-HauhauCS-Balanced · Q4_K_M 10.4 GB / 24 GB
✅ Runs comfortably

Adjacent comparisons