Qwen3.6-35B-A3B-FP8 vs HunyuanOCR
Specs, VRAM requirements and download trends — updated 3 October 2026.
Qwen · A · Open weights
Params
36.0 B
Context
—
30d
3.5 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-FP8 | HunyuanOCR |
|---|---|---|
| Parameters | 36.0 B | 1.1 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | HunYuanVLForConditionalGeneration |
| Context length | — | — |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 3 |
| Downloads 30d | 3,520,129 | 852,035 |
| Downloads all time | 46.9 M | 7.0 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2025-11-18 |
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
13.5 M841 K
Qwen3.6-35B-A3B-FP8
HunyuanOCR
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
HunyuanOCR · fp16
5.7 GB / 24 GB
Qwen3.6-35B-A3B-FP8 · fp16
47.1 GB / 24 GB