Qwen3-4B vs Ministral-3-8B-Instruct-2512
Specs, VRAM requirements and download trends — updated 24 October 2026.
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 | Qwen3-4B | Ministral-3-8B-Instruct-2512 |
|---|---|---|
| Deployment | Open weights | Open weights · also via API |
| Parameters | 4.0 B | 8.9 B |
| Architecture | Qwen3ForCausalLM | Mistral3ForConditionalGeneration |
| Context length | 40,960 | 262,144 |
| Licence | apache-2.0 | apache-2.0 |
| Commercial use | Allowed | Allowed |
| Languages | — | 11 |
| Downloads 30d | 11,396,683 | 93,976 |
| Downloads all time | 92.7 M | 1.2 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2025-04-27 | 2025-10-31 |
| API input price / 1M tokens | not on OpenRouter | $0.15 |
| API output price / 1M tokens | not on OpenRouter | $0.15 |
| Est. cost per 1M input + 1M output tokens | not on OpenRouter | $0.30 |
| Cached input / 1M tokens | not on OpenRouter | $0.015 |
| AA Intelligence Index | not on OpenRouter | 5.5 |
| AA Coding Index | not on OpenRouter | 9.7 |
| AA Agentic Index | not on OpenRouter | 0.6 |
| Max output tokens | not on OpenRouter | 209,715 |
| API providers | not on OpenRouter | 1 |
| Tool calling | not on OpenRouter | Yes |
| Reasoning mode | not on OpenRouter | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Ministral-3-8B-Instruct-2512
$0.30
Download trend
Daily snapshots, last 89 days (28 Jul – 24 Oct)
12.6 M105 K
Qwen3-4B
Ministral-3-8B-Instruct-2512
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Qwen3-4B · fp16
10.0 GB / 24 GB
Ministral-3-8B-Instruct-2512 · fp16
24.8 GB / 24 GB