Ministral 3 14B

At the default Q4_K_M, 59 of 140 phones have enough estimated usable memory; 59 also reach 3+ tokens/s. On Mac, 52 of 54 exact configurations pass using that quant or a smaller tracked fallback.

Params
14B
Family
mistral
Released
2025-12
Tags
chat · vision · reasoning

Downloads & memory by quant

The download is only the weights — add KV cache and runtime to get what your phone actually needs. “Memory-fit” only means it can load; “usable” also requires an estimated 3+ tokens/s. Each row uses that row's quant. ★ = recommended.

QuantDownloadMemory neededPhone reality
Q4_K_M8.2 GB~10.2 GB59 memory-fit · 59 usable
Q5_K_M9.6 GB~11.7 GB59 memory-fit · 59 usable
Q8_014.4 GB~16.7 GB3 memory-fit · 0 usable

Ministral 3 14B at Q4_K_M on 140 phones

This table is fixed to the recommended Q4_K_M, on each phone's largest RAM option. Counts for smaller quants above will differ. All phones are shown, sorted by fit and estimated experience; tap one for the full report.

PhoneChip · RAMNeedsSpeedVerdict

~ = bandwidth-based estimate · ✓ = measured on real hardware

Ministral 3 14B on 54 Mac configurations

Each Mac uses the recommended Q4_K_M at 4K context when it fits, or the largest smaller tracked quant that fits. Each row links to the full report with a macOS-specific setup guide.

MacUnified memoryQuantWorking budgetNeedsEstimated speedVerdict

FAQ

How much RAM do I need to run Ministral 3 14B on a phone?

At Q4_K_M, Ministral 3 14B needs ~10.2GB of usable memory (weights + KV cache + runtime). In practice that means a 16GB+ Android phone or a 16GB+ iPhone — iOS lets a single app use less of its RAM than Android does.

How fast does Ministral 3 14B run on a flagship phone?

On the OnePlus 13 (Snapdragon 8 Elite) it runs at ~4.2 tokens/s at Q4_K_M, estimated from memory bandwidth. Anything above ~8 tokens/s feels smooth for chat.

Can an iPhone run Ministral 3 14B?

Not really: the best iPhone we track (iPhone Air) has ~7.8GB usable, but Ministral 3 14B needs 10.2GB at Q4_K_M.

What is the best quantization of Ministral 3 14B for mobile?

Q4_K_M (8.2GB download) is the size/quality sweet spot of the 3 quants available. Total memory needed is ~10.2GB once the KV cache and runtime are counted — the download size alone understates it.

How many phones can run Ministral 3 14B?

59 of the 140 phones we track have enough estimated usable memory at Q4_K_M; 59 also reach our usable-speed threshold of 3 tokens/s, and 0 run smoothly. Memory-fit alone does not mean a good experience.

Which Macs can run Ministral 3 14B?

52 of the 54 exact Mac configurations we track have enough estimated working memory. Each Mac uses the recommended Q4_K_M when it fits, or the largest smaller tracked quant that fits, and separates installed unified memory, the macOS reserve, and estimated speed.

What is Ministral 3 14B good for on a phone?

It's tagged for chat, vision, reasoning. At 14B parameters, it prioritizes answer quality over speed — expect slower decoding.

Similar models

Mistral 7B v0.3Ministral 8BMinistral 3 3BMinistral 3 8BPhi-4 14B