Qwen3-32B vs gpt-oss-20b
Specs, VRAM requirements and download trends — updated 10 November 2026.
openai · B · Open weights
Params
21.5 B
Context
131,072
30d
5.8 M
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-32B | gpt-oss-20b |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 32.8 B | 21.5 B |
| Architecture | Qwen3ForCausalLM | GptOssForCausalLM |
| Context length | 40,960 | 131,072 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | — |
| Downloads 30d | 2,980,175 | 5,830,063 |
| Downloads all time | 62.7 M | 108.5 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2025-08-04 |
| API input price / 1M tokens | $0.08 | $0.03 |
| API output price / 1M tokens | $0.28 | $0.13 |
| Est. cost per 1M input + 1M output tokens | $0.36 | $0.16 |
| Cached input / 1M tokens | — | $0.03 |
| AA Intelligence Index | — | — |
| AA Coding Index | 15.3 | 20.7 |
| AA Agentic Index | 0.9 | 1.2 |
| Max output tokens | 16,384 | 117,964 |
| API providers | 3 | 10 |
| Tool calling | Yes | Yes |
| Reasoning mode | Yes | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen3-32B
$0.36
gpt-oss-20b
$0.16
gpt-oss-20b is 2.3× cheaper at list price.
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
8.1 M2.8 M
Qwen3-32B
gpt-oss-20b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-32B · fp16
77.5 GB / 24 GB
gpt-oss-20b · fp16 @ 128K ctx
82.4 GB / 24 GB