DeepSeek-R1-0528-Qwen3-8B vs Fanar-1-9B-Instruct
Specs, VRAM requirements and download trends — updated 31 July 2026.
deepseek-ai · A · Open weights
Params
8.2 B
Context
131,072
30d
354 K
mit · commercial OK
QCRI · B · Open weights
Params
8.8 B
Context
4,096
30d
195 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | DeepSeek-R1-0528-Qwen3-8B | Fanar-1-9B-Instruct |
|---|---|---|
| Parameters | 8.2 B | 8.8 B |
| Architecture | Qwen3ForCausalLM | Gemma2ForCausalLM |
| Context length | 131,072 | 4,096 |
| Licence | mit | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 2 |
| Downloads 30d | 354,073 | 195,303 |
| Downloads all time | 8.3 M | 825 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-05-29 | 2025-06-01 |
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
2.0 M195 K
DeepSeek-R1-0528-Qwen3-8B
Fanar-1-9B-Instruct
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Fanar-1-9B-Instruct · fp16
21.1 GB / 24 GB
DeepSeek-R1-0528-Qwen3-8B · fp16 @ 128K ctx
38.2 GB / 24 GB