Qwen-72B vs Llama-3_3-Nemotron-Super-49B-v1_5-FP8
Specs, VRAM requirements and download trends — updated 19 September 2026.
nvidia · B · Open weights
Params
49.9 B
Context
131,072
30d
204 K
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen-72B | Llama-3_3-Nemotron-Super-49B-v1_5-FP8 |
|---|---|---|
| Parameters | 72.3 B | 49.9 B |
| Architecture | QWenLMHeadModel | DeciLMForCausalLM |
| Context length | 32,768 | 131,072 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 2 | 1 |
| Downloads 30d | 157,322 | 203,999 |
| Downloads all time | 7.5 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-11-26 | 2025-07-31 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
4.2 M157 K
Qwen-72B
Llama-3_3-Nemotron-Super-49B-v1_5-FP8
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen-72B · fp16
170.4 GB / 24 GB
Llama-3_3-Nemotron-Super-49B-v1_5-FP8 · fp16 @ 128K ctx
177.4 GB / 24 GB