DeepSeek-R1-0528-Qwen3-8B vs Qwen2.5-Coder-7B-Instruct-AWQ
Specs, VRAM requirements and download trends — updated 2 August 2026.
deepseek-ai · A · Open weights
Params
8.2 B
Context
131,072
30d
371 K
mit · commercial OK
Orion-zhen · B · Open weights
Params
7.6 B
Context
32,768
30d
152 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-R1-0528-Qwen3-8B | Qwen2.5-Coder-7B-Instruct-AWQ |
|---|---|---|
| Parameters | 8.2 B | 7.6 B |
| Architecture | Qwen3ForCausalLM | Qwen2ForCausalLM |
| Context length | 131,072 | 32,768 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 370,533 | 151,880 |
| Downloads all time | 8.6 M | 2.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-05-29 | 2024-09-20 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.3 M152 K
DeepSeek-R1-0528-Qwen3-8B
Qwen2.5-Coder-7B-Instruct-AWQ
A overtook B on 29 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Coder-7B-Instruct-AWQ · fp16
7.9 GB / 24 GB
DeepSeek-R1-0528-Qwen3-8B · fp16 @ 128K ctx
38.2 GB / 24 GB