Qwen3.8-27B-FP8 vs Qwen3.5-35B-A3B-FP8
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · B · Open weights
Params
36.0 B
Context
—
30d
1.3 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.8-27B-FP8 | Qwen3.5-35B-A3B-FP8 |
|---|---|---|
| Parameters | 27.8 B | 36.0 B |
| Architecture | Qwen3_5ForConditionalGeneration | Qwen3_5MoeForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 5,285,294 | 1,278,450 |
| Downloads all time | 17.6 M | 13.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-08-13 | 2026-02-25 |
Download trend
Daily snapshots, last 83 days (20 Aug – 10 Nov)
7.9 M944 K
Qwen3.8-27B-FP8
Qwen3.5-35B-A3B-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.8-27B-FP8 · fp16
38.6 GB / 24 GB
Qwen3.5-35B-A3B-FP8 · fp16
47.1 GB / 24 GB