Qwen3.6-35B-A3B-NVFP4 vs Qwen2.5-32B-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-NVFP4 | Qwen2.5-32B-Instruct |
|---|---|---|
| Parameters | 18.7 B | 32.8 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Qwen2ForCausalLM |
| Context length | — | 32,768 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 11,298,952 | 1,745,648 |
| Downloads all time | 19.7 M | 27.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2024-09-17 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
11.3 M1.4 M
Qwen3.6-35B-A3B-NVFP4
Qwen2.5-32B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB
Qwen2.5-32B-Instruct · fp16
77.5 GB / 24 GB