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 Sep 2, 2026Ministral 3 is a compact text-and-image model from Mistral AI with a permissive Apache licence and a 131,072-token request limit. At 3.8 billion parameters it is built for edge hardware and very low-cost hosted inference rather than peak capability.
Pick this for Apache-licensed local or edge deployment where a 3.8-billion-parameter model fits your hardware, or for very low-cost hosted inference. Use it for lightweight image understanding with a permissive licence. Skip it if you need measured quality scores to validate performance, or if your workload demands frontier-level capability.
The case for it
- Apache 2.0 licence allows commercial use, fine-tuning and redistribution without restriction.
- Lowest published price among its own offers, with input and output rates matched at the cheapest tier.
- Fastest tier runs roughly three to four times the speed of its standard tiers.
The case against it
- No benchmark scores in our data — chat, reasoning, coding and multimodal quality are all unverified.
- 3.8 billion total parameters with no disclosed efficiency architecture to compensate for the compact size.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
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.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.10 in / $0.10 out
- Context served
- 131K
- Throughput
- ~42 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.10 / $0.10checked 4 hours ago | 131K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $0.10 / $0.10checked 4 hours ago | 131K105K max reply | 42 tok/s | No | Yes30 days | Confirmed |
| Mistral AIeuThrough OpenRouter | $0.11 / $0.11checked 4 hours ago | 131K105K max reply | 118 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 2 appear in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
Models people weigh against Ministral 3 3B 2512
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
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 independent board has scored it, 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 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
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
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- mistralai-ministral-3-3b-2512