DeepSeek-R1-0528-Qwen3-8B vs Meta-Llama-3-8B
Specs, VRAM requirements and download trends — updated 21 August 2026.
deepseek-ai · A · Open weights
Params
8.2 B
Context
131,072
30d
354 K
mit · commercial OK
meta-llama · B · Open weights
Params
8.0 B
Context
—
30d
139 K
llama3 licence · conditional
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-R1-0528-Qwen3-8B | Meta-Llama-3-8B |
|---|---|---|
| Parameters | 8.2 B | 8.0 B |
| Architecture | Qwen3ForCausalLM | LlamaForCausalLM |
| Context length | 131,072 | — |
| Licence | mit | llama3 |
| Commercial use | Allowed | Conditional |
| Languages | — | 1 |
| Downloads 30d | 354,073 | 139,310 |
| Downloads all time | 8.3 M | 47.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | Yes — accept licence |
| First seen on the Hub | 2025-05-29 | 2024-04-17 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
2.1 M139 K
DeepSeek-R1-0528-Qwen3-8B
Meta-Llama-3-8B
A overtook B on 29 Aug
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Meta-Llama-3-8B · fp16
19.4 GB / 24 GB
DeepSeek-R1-0528-Qwen3-8B · fp16 @ 128K ctx
38.2 GB / 24 GB