Qwen3.6-35B-A3B-FP8 vs Qwen2.5-VL-32B-Instruct
Specs, VRAM requirements and download trends — updated 6 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-FP8 | Qwen2.5-VL-32B-Instruct |
|---|---|---|
| Parameters | 36.0 B | 33.5 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Qwen2_5_VLForConditionalGeneration |
| Context length | — | 128,000 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 8,946,336 | 1,104,467 |
| Downloads all time | 24.7 M | 10.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-15 | 2025-03-21 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
8.9 M852 K
Qwen3.6-35B-A3B-FP8
Qwen2.5-VL-32B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-FP8 · fp16
47.1 GB / 24 GB
Qwen2.5-VL-32B-Instruct · fp16 @ 125K ctx
154.0 GB / 24 GB