Qwen3.8-27B vs gemma-4-26B-A4B-it-FP8-dynamic

Specs, VRAM requirements and download trends — updated 21 September 2026.

Qwen · A
Params
27.8 B
Context
30d
7.3 M
apache-2.0 · commercial OK
RedHatAI · B
Params
26.5 B
Context
30d
948 K
apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification Qwen3.8-27B gemma-4-26B-A4B-it-FP8-dynamic
Parameters 27.8 B 26.5 B
Architecture Qwen3_5ForConditionalGeneration Gemma4ForConditionalGeneration
Context length
Licence apache-2.0 apache-2.0
Commercial use Allowed Allowed
Languages
Downloads 30d 7,331,932 947,519
Downloads all time 9.4 M 5.2 M
Quantizations on the Hub SAFETENSORS SAFETENSORS
Gated No No
First seen on the Hub 2026-08-05 2026-04-06

Download trend

Daily snapshots, last 33 days (20 Aug – 21 Sep)

7.8 M835 K
Qwen3.8-27B gemma-4-26B-A4B-it-FP8-dynamic

VRAM side by side

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

gemma-4-26B-A4B-it-FP8-dynamic · fp16 36.0 GB / 24 GB
❌ Won’t fit
Qwen3.8-27B · fp16 65.8 GB / 24 GB
❌ Won’t fit

Adjacent comparisons