gpt-oss-20b vs Qwen2.5-Math-7B-4bit
Specs, VRAM requirements and download trends — updated 25 October 2026.
openai · A · 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 | gpt-oss-20b | Qwen2.5-Math-7B-4bit |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 21.5 B | 7.8 B |
| Architecture | GptOssForCausalLM | Qwen2ForCausalLM |
| Context length | 131,072 | 4,096 |
| Licence | apache-2.0 | — |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 5,764,154 | 168,211 |
| Downloads all time | 105.3 M | 262 K |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-08-04 | 2026-05-09 |
| API input price / 1M tokens | $0.018 | not on OpenRouter |
| API output price / 1M tokens | $0.09 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.11 | not on OpenRouter |
| Cached input / 1M tokens | $0.009 | not on OpenRouter |
| AA Intelligence Index | 10 | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 32,768 | not on OpenRouter |
| API providers | 10 | not on OpenRouter |
| Tool calling | Yes | not on OpenRouter |
| Reasoning mode | Yes | not on OpenRouter |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
gpt-oss-20b
$0.11
Download trend
Daily snapshots, last 90 days (28 Jul – 25 Oct)
8.6 M168 K
gpt-oss-20b
Qwen2.5-Math-7B-4bit
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-Math-7B-4bit · fp16
7.8 GB / 24 GB
gpt-oss-20b · fp16 @ 128K ctx
82.4 GB / 24 GB