Qwen3-30B-A3B vs gpt-neox-20b
Specs, VRAM requirements and download trends — updated 13 September 2026.
Qwen · A · Open weights
Params
30.5 B
Context
40,960
30d
1.1 M
apache-2.0 · commercial OK
EleutherAI · B · Open weights
Params
20.7 B
Context
2,048
30d
259 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-30B-A3B | gpt-neox-20b |
|---|---|---|
| Deployment | Open weights · also via API | Open weights |
| Parameters | 30.5 B | 20.7 B |
| Architecture | Qwen3MoeForCausalLM | GPTNeoXForCausalLM |
| Context length | 40,960 | 2,048 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 1 |
| Downloads 30d | 1,115,081 | 259,261 |
| Downloads all time | 23.2 M | 6.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2022-04-07 |
| API input price / 1M tokens | $0.12 | not on OpenRouter |
| API output price / 1M tokens | $0.50 | not on OpenRouter |
| Est. cost per 1M input + 1M output tokens | $0.62 | not on OpenRouter |
| Cached input / 1M tokens | — | not on OpenRouter |
| AA Intelligence Index | — | not on OpenRouter |
| AA Coding Index | — | not on OpenRouter |
| AA Agentic Index | — | not on OpenRouter |
| Max output tokens | 16,384 | not on OpenRouter |
| API providers | 1 | 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
Qwen3-30B-A3B
$0.62
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
2.7 M243 K
Qwen3-30B-A3B
gpt-neox-20b
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
gpt-neox-20b · fp16
49.0 GB / 24 GB
Qwen3-30B-A3B · fp16
72.3 GB / 24 GB