Yes — with 198.1 GB to spare

Ministral 3 8B at Q4_K_M fits your CPU only · DDR5 8-channel server entirely on the GPU at 8K context, at an estimated 26 tokens per second. There is room for its full 256K window.

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 198.1 GB of 204.8 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
F16 16.6 GB 18.3 GB 256K 7.7 Reference Long context
Q8_0 8.8 GB 10.5 GB 256K 15 −0.1% ppl Long context
Q6_K 6.8 GB 8.5 GB 256K 19 −0.4% ppl Long context
Q5_K_M 5.9 GB 7.6 GB 256K 22 −0.8% ppl Long context
Q4_K_M 5.0 GB 6.7 GB 256K 26 −1.9% ppl Recommended
Q3_K_M 4.1 GB 5.7 GB 256K 32 −5.4% ppl Long context
Q2_K 3.5 GB 5.1 GB 256K 37 −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.
02With no GPU, thread count matters more than clock. Start at one thread per physical core.
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

Related models on a CPU only · DDR5 8-channel server

ModelTotalTok/s est.
Ministral 3 14B
13.9B · same family
Q4_K_M · 9.7 GB 16 Runs great
Ministral 3 3B
3.85B · same family
Q4_K_M · 3.6 GB 59 Runs great
Granite 4.1 8B
8.79B · similar size
Q4_K_M · 6.8 GB 26 Runs great
LFM2.5 8B-A1B
8.47B MoE · similar size
Q4_K_M · 5.5 GB 68 Runs great
Ornith 1.5 9B
9.41B · similar size
Q4_K_M · 6.1 GB 24 Runs great
Fara 7B
8.29B · similar size
Q4_K_M · 5.7 GB 28 Runs great
Qwen3.5 9B
9.65B · similar size
Q4_K_M · 6.3 GB 24 Runs great

Every model against the CPU only · DDR5 8-channel server →

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 →