Yes, just — 0.3 GB spare

Ministral 3 8B at Q4_K_M fits your Arc A750 entirely on the GPU at 8K context, at an estimated 62 tokens per second. Past 10K 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 · 5.0 GB Apache 2.0 Released Dec 2025 Vision

Mistral's 8B with images in. Plain GQA, so budget more KV cache than Qwen3.5 9B at the same context.

Hardware requirements What hardware do I need to run Ministral 3 8B? →

At Q4_K_M with an 8K context: a 10 GB GPU (Arc B570) or a 16 GB Mac (M4). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 5.0 GB
Weights 5.0 GB KV cache @ 8K 1.06 GB Runtime overhead 0.6 GB Free 0.3 GB of 7.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 16.6 GB 18.3 GB — ~3.1 Reference 11.3 GB over
Q8_0 8.8 GB 10.5 GB — ~8.8 −0.1% ppl 3.5 GB over
Q6_K 6.8 GB 8.5 GB — ~17 −0.4% ppl 1.5 GB over
Q5_K_M 5.9 GB 7.6 GB 3K ~31 −0.8% ppl 0.6 GB over
Q4_K_M 5.0 GB 6.7 GB 10K 62 −1.9% ppl Recommended
Q3_K_M 4.1 GB 5.7 GB 17K 76 −5.4% ppl Long context
Q2_K 3.5 GB 5.1 GB 21K 89 −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-3-8B-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 5.0 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 0.3 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 10K context.
See all models for this rig Compare with another model

Related models on an Arc A750

ModelTotalTok/s est.
Ministral 3 14B
13.9B · same family
Q4_K_M · 9.7 GB ~11 CPU offload
Ministral 3 3B
3.85B · same family
Q4_K_M · 3.6 GB 143 Runs great
Granite 4.1 8B
8.79B · similar size
Q4_K_M · 6.8 GB 63 Tight fit
LFM2.5 8B-A1B
8.47B MoE · similar size
Q4_K_M · 5.5 GB 141 Runs great
Ornith 1.5 9B
9.41B · similar size
Q4_K_M · 6.1 GB 59 Tight fit
Fara 7B
8.29B · similar size
Q4_K_M · 5.7 GB 66 Runs great
Qwen3.5 9B
9.65B · similar size
Q4_K_M · 6.3 GB 57 Tight fit

Every model against the Arc A750 →

Ministral 3 8B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
6.7 GB 31 Tight fit
Arc B570
8.8 GB usable · 380 GB/s
6.7 GB 46 Runs great
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
6.7 GB 43 Runs great
M4 · 16 GB
10.7 GB usable · 120 GB/s
6.7 GB 13 Runs great
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
6.7 GB 122 Runs great
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
6.7 GB 116 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
6.7 GB 45 Runs great

All 114 devices, by tier →