Qwen-72B vs Qwen3-Coder-Next-FP8-dynamic
Specs, VRAM requirements and download trends — updated 17 September 2026.
RedHatAI · B
Params
79.8 B
Context
262,144
30d
201 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen-72B | Qwen3-Coder-Next-FP8-dynamic |
|---|---|---|
| Parameters | 72.3 B | 79.8 B |
| Architecture | QWenLMHeadModel | Qwen3NextForCausalLM |
| Context length | 32,768 | 262,144 |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 2 | — |
| Downloads 30d | 4,220,611 | 200,940 |
| Downloads all time | 7.5 M | 870 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-11-26 | 2026-02-27 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
4.2 M201 K
Qwen-72B
Qwen3-Coder-Next-FP8-dynamic
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen-72B · fp16
170.4 GB / 24 GB
Qwen3-Coder-Next-FP8-dynamic · fp16 @ 256K ctx
473.2 GB / 24 GB