Qwen2.5-14B-Instruct-AWQ vs DeepSeek-R1-0528-Qwen3-8B
Specs, VRAM requirements and download trends — updated 30 July 2026.
Qwen · A · Open weights
Params
14.8 B
Context
32,768
30d
1.3 M
apache-2.0 · commercial OK
deepseek-ai · B · Open weights
Params
8.2 B
Context
131,072
30d
354 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-14B-Instruct-AWQ | DeepSeek-R1-0528-Qwen3-8B |
|---|---|---|
| Parameters | 14.8 B | 8.2 B |
| Architecture | Qwen2ForCausalLM | Qwen3ForCausalLM |
| Context length | 32,768 | 131,072 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | 1 | — |
| Downloads 30d | 1,348,999 | 354,073 |
| Downloads all time | 17.9 M | 8.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2025-05-29 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
2.5 M354 K
Qwen2.5-14B-Instruct-AWQ
DeepSeek-R1-0528-Qwen3-8B
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-14B-Instruct-AWQ · fp16
13.7 GB / 24 GB
DeepSeek-R1-0528-Qwen3-8B · fp16 @ 128K ctx
38.2 GB / 24 GB