Ministral 3 8B 2512
Mistral AI · released Oct 31, 2025 · mistralai/Ministral-3-8B-Instruct-2512
- Type
- Open weightsApache License 2.0
- Params
- 8.9B
- Context
- 262K
about 197K words of context
Our take
Written Aug 4, 2026Ministral is a small downloadable model with a permissive Apache licence and a 262,144-token request limit. It is built for edge and low-memory deployment: on-device and laptop-local use rather than server workloads.
Pick this for edge and on-device deployment where every gigabyte of memory counts, or laptop-local inference in the 8GB unified-memory class. Its symmetric input and output pricing suits generation-heavy workloads. Skip it if you need a broad hosting market or measured quality scores.
The case for it
- 8.9 billion parameters: small enough to fit comfortably in under 8GB of memory.
- Text and image input in a sub-9-billion-parameter model.
The case against it
- Only three current offers, a thin hosted market.
- No benchmark scores yet, so there is no measured quality data.
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. 15.5 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 23.5 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Room to spare. 4.7 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 2 hours ago — each listing carries its own date.
- per 1M tokens
- $0.15 in / $0.15 out
- Context served
- 262K
- Throughput
- ~80 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.15 / $0.15checked 2 hours ago | 262K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $0.15 / $0.15checked 2 hours ago | 262K210K max reply | 80 tok/s | No | Yes30 days | Confirmed |
| Mistral AIeuThrough OpenRouter | $0.17 / $0.17checked 2 hours ago | 262K210K max reply | 76 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 8B 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-3-8B-Instruct-2512
- Architecture
- Dense
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- mistralai-ministral-3-8b-2512