Qwen2.5-72B-Instruct-AWQ vs MiniMax-M2.7
Specs, VRAM requirements and download trends — updated 4 August 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-72B-Instruct-AWQ | MiniMax-M2.7 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 73.0 B | 228.7 B |
| Architecture | Qwen2ForCausalLM | MiniMaxM2ForCausalLM |
| Context length | 32,768 | 204,800 |
| Licence | other | other |
| Commercial use | Unknown | Unknown |
| Languages | 1 | — |
| Downloads 30d | 252,438 | 302,065 |
| Downloads all time | 12.5 M | 8.1 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-17 | 2026-04-09 |
| API input price / 1M tokens | not on OpenRouter | $0.21 |
| API output price / 1M tokens | not on OpenRouter | $0.84 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $1.05 |
| Cached input / 1M tokens | not on OpenRouter | $0.042 |
| AA Intelligence Index | not on OpenRouter | — |
| AA Coding Index | not on OpenRouter | 52.6 |
| AA Agentic Index | not on OpenRouter | 15.3 |
| Max output tokens | not on OpenRouter | 176,947 |
| API providers | not on OpenRouter | 2 |
| 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-M2.7
$1.05
Download trend
Daily snapshots, last 90 days (13 Aug – 10 Nov)
1.5 M252 K
Qwen2.5-72B-Instruct-AWQ
MiniMax-M2.7
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-72B-Instruct-AWQ · fp16
57.2 GB / 24 GB
MiniMax-M2.7 · fp16 @ 200K ctx
1,111.2 GB / 24 GB