Ministral 3 3B 2512
Mistral AI · released Oct 31, 2025 · mistralai/Ministral-3-3B-Instruct-2512
- Type
- Open weightsApache License 2.0
- Params
- 3.8B
- Context
- 131K
about 98K words of context
Our take
Written Aug 3, 2026Ministral 3 is a small downloadable model from Mistral AI that accepts text and images and returns text. It carries a permissive Apache licence and a 131,072-token request limit, but no benchmark scores have been measured yet.
Pick this for basic vision-language tasks where cost matters and you need a permissive licence for redistribution or fine-tuning. Use it if you want identical pricing across the two tracked providers with no markup. Skip it if you need measured quality data to justify your choice, or if you require verified throughput on every host you use.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution.
- Identical pricing across both tracked providers, with no markup between them.
- Among the cheapest listed rates for multimodal models.
The case against it
- No benchmark scores in the catalogue — no measured quality data of any kind.
- Throughput undisclosed on one of two offers; only one host lists a speed figure.
- 3.8 billion total parameters with no efficiency architecture disclosed.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up Ministral 3 3B 2512 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Can you run it yourself?
- Fits in memory
- weights load entirely on the card
- Spills to system RAM
- some weights offload; much slower
- Too large
- will not load even with offload
- est
- size is calculated; the verdict could change by 10%
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 18.9 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 26.9 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 2.1 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
All 3 sizes here are calculated, not measured. We hold no measured file for this model, so each size comes from the parameter count and every verdict above inherits that uncertainty.
Check against your own machine → · All 71 devices, with every size →
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.10 in / $0.10 out
- Context served
- 131K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.10 / $0.10 | 131K | not measured | Unknown | Unknown | Unknown |
| Mistral AI | $0.10 / $0.10 | 131K | 44 tok/s | No | Yes30 days | Unknown |
Mistral AIAcross the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| Mistral AI | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against Ministral 3 3B 2512
When we formed this view
Dates behind this page
Prices last checked 38h ago
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- mistralai/Ministral-3-3B-Instruct-2512
- Architecture
- Dense
- Modality record
- text+image->text
- Catalogue slug
- mistralai-ministral-3-3b-2512