Qwen3-235B-A22B vs MiniMax-M2.5
Specs, VRAM requirements and download trends — updated 10 November 2026.
Qwen · A · Open weights
Params
235.1 B
Context
40,960
30d
307 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen3-235B-A22B | MiniMax-M2.5 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 235.1 B | 228.7 B |
| Architecture | Qwen3MoeForCausalLM | MiniMaxM2ForCausalLM |
| Context length | 40,960 | 196,608 |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | — | — |
| Downloads 30d | 306,653 | 1,202,828 |
| Downloads all time | 7.7 M | 6.7 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2026-02-12 |
| API input price / 1M tokens | not on OpenRouter | $0.30 |
| API output price / 1M tokens | not on OpenRouter | $1.20 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.50 |
| Cached input / 1M tokens | not on OpenRouter | $0.06 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | — |
| AA Agentic Index | not on OpenRouter | — |
| Max output tokens | not on OpenRouter | 58,982 |
| API providers | not on OpenRouter | 5 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | Yes |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
MiniMax-M2.5
$1.50
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.4 M272 K
Qwen3-235B-A22B
MiniMax-M2.5
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-235B-A22B · fp16
553.0 GB / 24 GB
MiniMax-M2.5 · fp16 @ 192K ctx
1,076.9 GB / 24 GB