- Source
- Model registry API
- Verified
- 19 Sep 2026
- Confidence
- High
01What this is
- Author
- mistralai
- Family
- Ministral 3
- Task
- text-generation
- Hugging Face
- mistralai/Ministral-3-8B-Instruct-2512
- OpenRouter
- mistralai/ministral-8b-2512
- Also known as
- Ministral 3 8B, ministral-3-8b, ministral 8b
02Registry facts
- LicenceFACT
apache-2.0
- FreshRetrieved 19 Sep 2026
- ParametersFACT
8.9B
- FreshRetrieved 19 Sep 2026
- Context lengthFACT
not returned by the registry
- Evidence not verified
- Downloads (30 days)FACT
70,416
- FreshRetrieved 19 Sep 2026
- LikesFACT
203
- FreshRetrieved 19 Sep 2026
- GatedFACT
no
- FreshRetrieved 19 Sep 2026
Model
- downloadsFACT
70416
- Verification may be outdatedRetrieved 19 Sep 2026
- gatedFACT
false
- Verification may be outdatedRetrieved 19 Sep 2026
- hosted context length · MistralFACT
262144
- Verification may be outdatedRetrieved 19 Sep 2026
- likesFACT
203
- Verification may be outdatedRetrieved 19 Sep 2026
- model licenseFACT
apache-2.0
- Verification may be outdatedRetrieved 19 Sep 2026
- parameter countFACT
8918026716
- Verification may be outdatedRetrieved 19 Sep 2026
Pricing
- hosted price completion per m · MistralFACT
0.1650
- AgeingRetrieved 19 Sep 2026
- hosted price prompt per m · MistralFACT
0.1650
- AgeingRetrieved 19 Sep 2026
Other
- available on platform · vendorFACT
vendor
- AgeingRetrieved 19 Sep 2026
- available on platform · awsFACT
aws
The source document changed after this was recorded; it is queued for re-checking.
- Verification may be outdatedRetrieved 19 Sep 2026
- last modifiedFACT
2026-07-15T12:22:08.000Z
- Verification may be outdatedRetrieved 19 Sep 2026
- libraryFACT
vllm
- AgeingRetrieved 19 Sep 2026
03VRAM by quantisation
Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: 8.9B parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).
| Quantisation | Weights | Total |
|---|---|---|
| bf16bf16 is two bytes per weight, the same arithmetic as fp16. | 17.84 GB | 26.07 GB |
| int8 | 8.92 GB | 15.81 GB |
| q4_k_mSized as 4-bit weights. Q4_K_M averages nearer 4.5 bits in practice, so read this as a floor. | 4.46 GB | 10.68 GB |
What this estimate assumes
- Weights: 8.9B parameters × 2 bytes per parameter (fp16) = 17.84 GB.
- No model configuration was supplied, so the KV cache uses the size heuristic for this band: 0.147 MB per token, from Qwen3-8B (36 layers × 8 KV heads × 128 head dim).
- KV cache: 0.147 MB per token × 8,192 tokens of context × 4 concurrent requests = 4.83 GB, sized for every user holding a full context at once.
- Overhead: 15% of weights plus KV cache for the runtime, activations and memory fragmentation = 3.4 GB.
- GB means 10⁹ bytes, matching how GPU memory is advertised.
- KV cache held at fp16 (2 bytes per element); quantising weights does not by itself quantise the cache.
- Peak figure, not average: prefix caching and paged attention usually keep real usage lower, while speculative decoding, CUDA graphs and a second resident model push it higher.
- "Concurrent" counts requests generated at the same instant, not people: 4 simultaneous requests is the worst case this estimate is built on — measure yours before buying.
04Hardware profiles
No hardware profile was sized for this answer.
05Hosted providers
- Prompt (per million tokens, USD)FACT
0.15
Source: openrouter
- FreshRetrieved 19 Sep 2026
- Completion (per million tokens, USD)FACT
0.15
- FreshRetrieved 19 Sep 2026
| Provider | Context |
|---|---|
| Mistral | 262,144 |
| Mistral | 262,144 |
| Mistral | 262,144 |
06Deployment stacks
No published deployment stack names this model yet.
07Evidence
- 01Tier 2official vendor legal documentationVendor legal and technical documentation
https://docs.mistral.ai/models
AgeingRetrieved 19 Sep 2026sha256:75db4776a3cb1 record
- 02Tier 2official vendor legal documentationVendor legal and technical documentation
Models at a glance - Amazon Bedrock
https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards.html
AgeingRetrieved 19 Sep 2026sha256:4c3b2b5762261 record
- 03–05Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — mistralai/ministral-8b-2512
https://openrouter.ai/api/v1/models/mistralai/ministral-8b-2512/endpoints
AgeingRetrieved 19 Sep 2026sha256:5a26080b15483 records · ·
- 06–12Tier 4official repository / model cardHugging Face Hub
Hugging Face model card data — mistralai/Ministral-3-8B-Instruct-2512
https://huggingface.co/api/models/mistralai/Ministral-3-8B-Instruct-2512
Verification may be outdatedRetrieved 19 Sep 2026sha256:13f4d801098d7 records · · · · · ·
Improve this page
Sign in to contribute
From the field
0 deployments · 0 questions
Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.