diffusiongemma-26B-A4B-it vs Qwen3.8-27B-FP8
Specs, VRAM requirements and download trends — updated 13 September 2026.
google · A · Open weights
Params
25.8 B
Context
—
30d
841 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | diffusiongemma-26B-A4B-it | Qwen3.8-27B-FP8 |
|---|---|---|
| Parameters | 25.8 B | 27.8 B |
| Architecture | DiffusionGemmaForBlockDiffusion | Qwen3_5ForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 841,028 | 5,285,294 |
| Downloads all time | 5.2 M | 17.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-06-09 | 2026-08-13 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
7.9 M841 K
diffusiongemma-26B-A4B-it
Qwen3.8-27B-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.8-27B-FP8 · fp16
38.6 GB / 24 GB
diffusiongemma-26B-A4B-it · fp16
61.2 GB / 24 GB