DeepSeek-R1-0528-Qwen3-8B vs Llama-2-7b-hf
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
meta-llama · B · Open weights
Params
6.7 B
Context
—
30d
211 K
llama2 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-R1-0528-Qwen3-8B | Llama-2-7b-hf |
|---|---|---|
| Parameters | 8.2 B | 6.7 B |
| Architecture | Qwen3ForCausalLM | LlamaForCausalLM |
| Context length | 131,072 | — |
| Licence | mit | llama2 |
| Commercial use | Allowed | Conditional |
| Languages | — | 1 |
| Downloads 30d | 370,533 | 210,766 |
| Downloads all time | 8.6 M | 35.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2025-05-29 | 2023-07-13 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.3 M211 K
DeepSeek-R1-0528-Qwen3-8B
Llama-2-7b-hf
A overtook B on 31 Oct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Llama-2-7b-hf · fp16
16.3 GB / 24 GB
DeepSeek-R1-0528-Qwen3-8B · fp16 @ 128K ctx
38.2 GB / 24 GB