Qwen2.5-7B-Instruct vs Ministral-3-8B-Instruct-2512
Specs, VRAM requirements and download trends — updated 24 October 2026.
Qwen · A · Open weights
Params
7.6 B
Context
32,768
30d
6.4 M
apache-2.0 · commercial OK
mistralai · B · Open weights
Params
8.9 B
Context
—
30d
94 K
apache-2.0 · commercial OK
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Qwen2.5-7B-Instruct | Ministral-3-8B-Instruct-2512 |
|---|---|---|
| Deployment | Open weights · also via API | Open weights · also via API |
| Parameters | 7.6 B | 8.9 B |
| Architecture | Qwen2ForCausalLM | Mistral3ForConditionalGeneration |
| Context length | 32,768 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | 1 | 11 |
| Downloads 30d | 6,369,723 | 93,976 |
| Downloads all time | 190.0 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2024-09-16 | 2025-10-31 |
| API input price / 1M tokens | $0.10 | $0.15 |
| API output price / 1M tokens | $0.20 | $0.15 |
| Est. cost per 1M input + 1M output tokens | $0.30 | $0.30 |
| Cached input / 1M tokens | — | $0.015 |
| AA Intelligence Index | — | 5.5 |
| AA Coding Index | — | 9.7 |
| AA Agentic Index | — | 0.6 |
| Max output tokens | 29,491 | 209,715 |
| API providers | 1 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Qwen2.5-7B-Instruct
$0.30
Ministral-3-8B-Instruct-2512
$0.30
Ministral-3-8B-Instruct-2512 is 1.0× cheaper at list price.
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
12.3 M105 K
Qwen2.5-7B-Instruct
Ministral-3-8B-Instruct-2512
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen2.5-7B-Instruct · fp16
18.4 GB / 24 GB
Ministral-3-8B-Instruct-2512 · fp16
24.8 GB / 24 GB