Mistral AI
Mistral AI
Language model · France ·Oct 2024

Ministral 8B

Language Open Weights
8B
Parameters
19
Benchmarks

About Ministral 8B

Ministral 8B is an AI model developed by Mistral AI, in the language category, released in 2024, made available as an open-weights model with 8B params.

On this page you'll find Ministral 8B's full specifications, including 19 benchmark results. Review provider pricing and benchmark scores below, or compare Ministral 8B head-to-head with other language models.

Links

Run Ministral 8B locally — what to buy

Share this build ↗

Sized to what Ministral 8B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.

Software support

✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.

Community

Would you run Ministral 8B again?
No votes yet — be the first.
Did it run? — community reports by hardware

No reports yet. Own this model on some hardware? Be the first to confirm it runs.

Discussion

No comments yet. Start the discussion.

Ministral 8B benchmark scores
Benchmark Category Score Variant
HumanEval code 91% instruct-pass@10-cited-tulu3
HumanEval+ code 88.5% instruct-pass@10-cited-tulu3
AlpacaEval 2 general 31.4% instruct-lc-win-cited-tulu3
ArenaHard general 26.9% cited-phi4-mini
IFEval general 56.4% instruct-cited-tulu3
MMLU general 60.8% cited-phi4-mini
MMLU-Pro general 35.3% cited-phi4-mini
MMMLU general 46.4% cited-phi4-mini
ARC-Challenge knowledge 80.3 cited-phi4-mini
GSM8K math 80.1% cited-phi4-mini
MATH math 41.8% cited-phi4-mini
MGSM math 44.6 cited-phi4-mini
BIG-Bench Hard reasoning 51.2% cited-phi4-mini
DROP reasoning 56.2% instruct-cited-tulu3
HellaSwag reasoning 74.6 cited-phi4-mini
PIQA reasoning 73.2 cited-phi4-mini
Winogrande reasoning 59.8 cited-phi4-mini
TruthfulQA safety 62.9% cited-phi4-mini
TruthfulQA safety 55.5% instruct-cited-tulu3

More models like Ministral 8B

Frequently asked questions

What is Ministral 8B?

Ministral 8B is an AI model developed by Mistral AI, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.

Who created Ministral 8B?

Ministral 8B was developed by Mistral AI and released in 2024.

Is Ministral 8B open source or proprietary?

Ministral 8B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.

How much does Ministral 8B cost?

Pricing for Ministral 8B depends on the provider. See the providers table on this page for the latest API rates.

How does Ministral 8B perform on benchmarks?

Ministral 8B is benchmarked across 19 evaluations on GenAIList, including HumanEval (91%). See the full benchmark table below and compare it with other models.

Fine Tuning Ministral 8B - Step by Step Guide
Mistral AI introduces Ministral 3B & 8B | Most capable small language models!?
New Mistral Models are too Good: Ministral 3B and 8B | Quality Testing on Virtual GPUs
Can Mistral's 8B Model Actually Code? I Spent 2 Hours Building an Airbnb Clone with Ministral 3.
Local AI on Mac Mini M4: Testing Ministral 3B, 8B & 14B

Know a great video about Ministral 8B?