Qwen3.6-35B-A3B-NVFP4 vs Qwen2.5-7B-Instruct-1M
Specs, VRAM requirements and download trends — updated 16 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3.6-35B-A3B-NVFP4 | Qwen2.5-7B-Instruct-1M |
|---|---|---|
| Parameters | 18.7 B | 7.6 B |
| Architecture | Qwen3_5MoeForConditionalGeneration | Qwen2ForCausalLM |
| Context length | — | 1,010,000 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 8,020,372 | 197,266 |
| Downloads all time | 34.6 M | 10.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-05-27 | 2025-01-23 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
12.6 M173 K
Qwen3.6-35B-A3B-NVFP4
Qwen2.5-7B-Instruct-1M
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3.6-35B-A3B-NVFP4 · fp16
29.1 GB / 24 GB
Qwen2.5-7B-Instruct-1M · fp16 @ 986K ctx
158.2 GB / 24 GB