Qwen-72B vs Qwen3-VL-30B-A3B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 30 September 2026.
QuantTrio · B · Open weights
Params
31.1 B
Context
—
30d
163 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen-72B | Qwen3-VL-30B-A3B-Instruct-AWQ |
|---|---|---|
| Parameters | 72.3 B | 31.1 B |
| Architecture | QWenLMHeadModel | Qwen3VLMoeForConditionalGeneration |
| Context length | 32,768 | — |
| Licence | other | apache-2.0 |
| Commercial use | Unknown | Allowed |
| Languages | 2 | — |
| Downloads 30d | 157,322 | 162,536 |
| Downloads all time | 7.5 M | 9.8 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2023-11-26 | 2025-10-04 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
4.2 M157 K
Qwen-72B
Qwen3-VL-30B-A3B-Instruct-AWQ
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-VL-30B-A3B-Instruct-AWQ · fp16
24.8 GB / 24 GB
Qwen-72B · fp16
170.4 GB / 24 GB
Adjacent comparisons
Gemma-4-31B-IT-NVFP4 vs Qwen-72B
Gemma-4-31B-IT-NVFP4 vs Qwen3-VL-30B-A3B-Instruct-AWQ
Qwen-72B vs Qwen3.8-27B-Heretic-Abliterated-Uncensored-GGUF
Qwen2.5-Coder-14B-Instruct vs Qwen3-VL-30B-A3B-Instruct-AWQ
Qwen2.5-14B-Instruct vs Qwen3-VL-30B-A3B-Instruct-AWQ
Qwen3-VL-30B-A3B-Instruct-AWQ vs Qwen2.5-Coder-32B-Instruct