Ministral-3-14B-Instruct-2512
mistralai/Ministral-3-14B-Instruct-2512
Official · BF16 · safetensors
Runtime certified: vLLM
| Precision / quantization | Format | Bits | Publisher trust | Deployment state |
|---|---|---|---|---|
| BF16 | safetensors | 16 | Official | Runtime certified |
Mistral · Ministral · Ministral 3
Ministral 3 14B Instruct 2512: Specs, GPU requirements, hosting & deployment
Ministral 3 14B Instruct 2512 is a current Ministral release in the Mistral family, certified from its immutable official source revision.
Total parameters14.0B
Active parametersDense model
Context window262,144 tokens
Release statusCurrent · Current
ArchitectureMistral3ForConditionalGeneration
ModalitiesText, Image
LicenseApache License 2.0
Deployment stateDeployable with certified configuration
Commercial stateCommercial Use Allowed
Release date2025-10-31
Architecture, strengths and use cases
Ministral 3 14B Instruct 2512 is an official self-hostable Mistral AI release in the Mistral Ministral track. It uses Mistral3ForConditionalGeneration, carries 14B, supports a verified context window of 262,144 tokens, and exposes only source-certified checkpoints and runtime combinations. Its release, license and deployment facts are tied to the official repository revision rather than inferred from the family name.
Ministral 3 14B Instruct 2512 uses Mistral3ForConditionalGeneration with 14B. The stored architecture profile records 40 layers, hidden width 5120, 32 attention heads and a 262,144 token context ceiling where the official configuration publishes those fields.
Verified Mistral3ForConditionalGeneration architecture
262,144 token certified context
Official BF16 checkpoint coverage
Private LLM inference
Agentic workflows
Long-context document processing
Vision-language analysis
Certified checkpoints and quantizations
Only exact, source-certified variants attached to this release are shown.
Recommended hardware
Use only the listed vllm runtime configuration with the exact checkpoint precision. The recommendation engine checks weight memory, KV cache, runtime overhead, safety headroom, GPU architecture and topology before ranking rentable and reference hardware.
Estimated weight memory26.86 GB
KV cache1.25 GB
Runtime overhead9.78 GB
Total with safety margin46.98 GB
Recommended best value
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
94.02 GB headroom · Limited capacity
USD 2,345 / monthLowest-cost viable
2× NVIDIA L4 24GB
48 GB total VRAM · pcie
1.02 GB headroom · Available
USD 500 / monthHighest performance
1× NVIDIA H200 SXM 141GB
141 GB total VRAM · nvswitch
94.02 GB headroom · Limited capacity
USD 2,345 / monthLicense and self-hosting considerations
The full 14B resident weight set must fit across the selected GPUs. Context and concurrency add KV-cache memory; MoE active parameters do not replace resident-weight memory.
Ministral 3 14B Instruct 2512 is published under Apache License 2.0. The release-scoped official license link and verification date are retained with the catalogue record.
Commercial Use Allowed. The official license permits commercial use; its obligations still apply.
Alternatives and sibling variants
Ministral 3 8B Instruct 2512, Ministral 3 3B Instruct 2512, Ministral-3-14B-Instruct-2512
Release timeline
mistral-ai/mistral/ministral-3-14b-instruct-2512 @ 14da8cf90107826392038e085efee53f886d7371dde31dc9ac6ca8b6868c6cc2
Frequently asked questions
How much VRAM does Ministral 3 14B Instruct 2512 require?
The exact estimate depends on checkpoint precision, context and concurrency; the page recommendation uses the certified memory engine and compatible runtime configurations.
Which runtimes support Ministral 3 14B Instruct 2512?
Certified upstream runtime evidence is available for vllm.
Can Ministral 3 14B Instruct 2512 be used commercially?
The stored commercial classification is Commercial Use Allowed. Consult the official Apache License 2.0 terms for the final obligations.
Official references
Last verified: 2026-08-26