DeepSeek-R1-0528-Qwen3-8B vs Qwen3-8B-FP8
Specs, VRAM requirements and download trends — updated 7 August 2026.
deepseek-ai · A · Open weights
Params
8.2 B
Context
131,072
30d
371 K
mit · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-R1-0528-Qwen3-8B | Qwen3-8B-FP8 |
|---|---|---|
| Parameters | 8.2 B | 8.2 B |
| Architecture | Qwen3ForCausalLM | Qwen3ForCausalLM |
| Context length | 131,072 | 40,960 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 370,533 | 224,647 |
| Downloads all time | 8.6 M | 5.6 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-05-29 | 2025-04-28 |
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.3 M225 K
DeepSeek-R1-0528-Qwen3-8B
Qwen3-8B-FP8
A overtook B on 3 Nov
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-8B-FP8 · fp16
12.1 GB / 24 GB
DeepSeek-R1-0528-Qwen3-8B · fp16 @ 128K ctx
38.2 GB / 24 GB