DeepSeek-V4-Flash vs Qwen-72B
Specs, VRAM requirements and download trends — updated 21 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-V4-Flash | Qwen-72B |
|---|---|---|
| Parameters | 158.1 B | 72.3 B |
| Architecture | DeepseekV4ForCausalLM | QWenLMHeadModel |
| Context length | 1,048,576 | 32,768 |
| Licence | mit | other |
| Commercial use | Allowed | Unknown |
| Languages | — | 2 |
| Downloads 30d | 1,559,750 | 4,220,611 |
| Downloads all time | 12.0 M | 7.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2026-04-22 | 2023-11-26 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
4.2 M1.4 M
DeepSeek-V4-Flash
Qwen-72B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen-72B · fp16
170.4 GB / 24 GB
DeepSeek-V4-Flash · fp16 @ 1024K ctx
3,211.0 GB / 24 GB