Yes, just — 0.9 GB spare

Ministral 3 14B at Q4_K_M fits your Arc B580 entirely on the GPU at 8K context, at an estimated 35 tokens per second. Past 13K 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 0.9 GB of 10.6 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 25.9 GB 27.7 GB — ~2.0 Reference 17.1 GB over
Q8_0 13.8 GB 15.6 GB — ~5.9 −0.1% ppl 5.0 GB over
Q6_K 10.6 GB 12.5 GB — ~12 −0.4% ppl 1.9 GB over
Q5_K_M 9.2 GB 11.0 GB 5K ~23 −0.8% ppl 0.4 GB over
Q4_K_M 7.8 GB 9.7 GB 13K 35 −1.9% ppl Recommended
Q3_K_M 6.3 GB 8.2 GB 23K 44 −5.4% ppl Long context
Q2_K 5.4 GB 7.3 GB 29K 51 −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
$ llama-server \
    -hf mistralai/Ministral-3-14B-Instruct-2512:Q4_K_M \
    -c 8192 -ngl 99

The engine underneath most of the others. Every knob is exposed. More on llama.cpp.

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.
03Only 0.9 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 13K context.
See all models for this rig Compare with another model

Related models on an Arc B580

ModelTotalTok/s est.
Ministral 3 8B
8.92B · same family
Q4_K_M · 6.7 GB 55 Runs great
Ministral 3 3B
3.85B · same family
Q4_K_M · 3.6 GB 128 Runs great
Phi-4 14B
14.7B · similar size
Q4_K_M · 10.4 GB 33 Tight fit
Qwen3 14B
14.8B · similar size
Q4_K_M · 10.2 GB 33 Tight fit
DeepSeek-R1-Distill-Qwen 14B
14.8B · similar size
Q4_K_M · 10.4 GB 33 Tight fit
Qwen2.5-Coder 14B
14.8B · similar size
Q4_K_M · 10.4 GB 33 Tight fit
Gemma 3 12B
12.2B · similar size
Q4_K_M · 8.3 GB 40 Runs great

Every model against the Arc B580 →

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 →