gpt-oss-120b vs DeepSeek-R1-0528-NVFP4-v2
Specs, VRAM requirements and download trends — updated 5 September 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | gpt-oss-120b | DeepSeek-R1-0528-NVFP4-v2 |
|---|---|---|
| Parameters | 120.4 B | 393.6 B |
| Architecture | GptOssForCausalLM | DeepseekV3ForCausalLM |
| Context length | 131,072 | 163,840 |
| Licence | apache-2.0 | mit |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 5,008,854 | 189,945 |
| Downloads all time | 57.0 M | 5.3 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2025-07-21 |
Download trend
Daily snapshots, last 56 days (28 Jul – 21 Sep)
5.5 M190 K
gpt-oss-120b
DeepSeek-R1-0528-NVFP4-v2
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt-oss-120b · fp16 @ 128K ctx
433.0 GB / 24 GB
DeepSeek-R1-0528-NVFP4-v2 · fp16 @ 160K ctx
1,636.1 GB / 24 GB