Yes — with 52.7 GB to spare

Ministral 3 14B at Q4_K_M fits your Instinct MI210 entirely on the GPU at 8K context, at an estimated 127 tokens per second. There is room for its full 256K window.

Fully on GPU 8K context Q4_K_M · 7.8 GB Apache 2.0 Released Dec 2025 Vision

The largest Ministral. A 12 GB card runs it at Q4 with a few gigabytes to spare.

What hardware do I need for Ministral 3 14B? →

The VRAM budget

weights 7.8 GB
Weights 7.8 GB KV cache @ 8K 1.25 GB Runtime overhead 0.6 GB Free 52.7 GB of 62.4 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 25.9 GB 27.7 GB 229K 38 Reference Long context
Q8_0 13.8 GB 15.6 GB 256K 72 −0.1% ppl Long context
Q6_K 10.6 GB 12.5 GB 256K 93 −0.4% ppl Long context
Q5_K_M 9.2 GB 11.0 GB 256K 108 −0.8% ppl Long context
Q4_K_M 7.8 GB 9.7 GB 256K 127 −1.9% ppl Recommended
Q3_K_M 6.3 GB 8.2 GB 256K 157 −5.4% ppl Long context
Q2_K 5.4 GB 7.3 GB 256K 183 −15% ppl Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

terminal
$ ollama pull ministral-3:14b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run ministral-3:14b

The default. One binary, a model registry, an OpenAI-compatible port. More on Ollama.

01Download is 7.8 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.
02Close anything else holding VRAM. A browser with hardware acceleration can sit on 1–2 GB.
03There is room to go to the model's full 256K context on this card.
See all models for this rig Compare with another model