Yes — with 35.1 GB to spare

Ministral 3 14B at Q4_K_M fits your 2× GeForce RTX 3090 entirely on the GPUs at 8K context, at an estimated 72 tokens per second. Past 232K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

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.

Hardware requirements What hardware do I need to run Ministral 3 14B? →

At Q4_K_M with an 8K context: a 16 GB GPU (RTX 5080) or a 24 GB Mac (M4 Pro). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 7.8 GB
Weights 7.8 GB KV cache @ 8K 1.25 GB Runtime overhead 0.6 GB Free 35.1 GB of 44.8 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 25.9 GB 27.7 GB 117K 22 Reference Long context
Q8_0 13.8 GB 15.6 GB 194K 41 −0.1% ppl Long context
Q6_K 10.6 GB 12.5 GB 214K 53 −0.4% ppl Long context
Q5_K_M 9.2 GB 11.0 GB 224K 62 −0.8% ppl Long context
Q4_K_M 7.8 GB 9.7 GB 232K 72 −1.9% ppl Recommended
Q3_K_M 6.3 GB 8.2 GB 242K 90 −5.4% ppl Long context
Q2_K 5.4 GB 7.3 GB 248K 105 −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.
02llama.cpp and Ollama spread the layers over both cards on their own. The cards take turns on every token, so expect about one card's speed; vLLM's --tensor-parallel-size 2 runs them in parallel instead.
03There is room to go to 232K context on this card.
See all models for this rig Compare with another model

Related models on a 2× GeForce RTX 3090

ModelTotalTok/s est.
Ministral 3 8B
8.92B · same family
Q4_K_M · 6.7 GB 113 Runs great
Ministral 3 3B
3.85B · same family
Q4_K_M · 3.6 GB 262 Runs great
Phi-4 14B
14.7B · similar size
Q4_K_M · 10.4 GB 69 Runs great
Qwen3 14B
14.8B · similar size
Q4_K_M · 10.2 GB 68 Runs great
DeepSeek-R1-Distill-Qwen 14B
14.8B · similar size
Q4_K_M · 10.4 GB 68 Runs great
Qwen2.5-Coder 14B
14.8B · similar size
Q4_K_M · 10.4 GB 68 Runs great
Gemma 3 12B
12.2B · similar size
Q4_K_M · 8.3 GB 83 Runs great

Every model against the 2× GeForce RTX 3090 →

Ministral 3 14B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
9.7 GB ~9.4 CPU offload
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
9.7 GB 28 Tight fit
GeForce RTX 5080
14.4 GB usable · 960 GB/s
9.7 GB 74 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
9.7 GB 8.6 Tight fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
9.7 GB 78 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
9.7 GB 74 Runs great
M4 Pro · 24 GB
18.0 GB usable · 273 GB/s
9.7 GB 20 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
9.7 GB 29 Runs great

All 114 devices, by tier →