Yes — with 15.7 GB to spare

Ministral 3 8B at Q4_K_M fits your Tesla P40 entirely on the GPU at 8K context, at an estimated 42 tokens per second. Past 126K 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.

What hardware do I need for Ministral 3 8B? →

The VRAM budget

weights 5.0 GB

Weights 5.0 GB KV cache @ 8K 1.06 GB Runtime overhead 0.6 GB Free 15.7 GB of 22.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
F16	16.6 GB	18.3 GB	39K	13	Reference	Long context
Q8_0	8.8 GB	10.5 GB	97K	24	−0.1% ppl	Long context
Q6_K	6.8 GB	8.5 GB	112K	31	−0.4% ppl	Long context
Q5_K_M	5.9 GB	7.6 GB	119K	36	−0.8% ppl	Long context
Q4_K_M	5.0 GB	6.7 GB	126K	42	−1.9% ppl	Recommended
Q3_K_M	4.1 GB	5.7 GB	133K	52	−5.4% ppl	Long context
Q2_K	3.5 GB	5.1 GB	137K	60	−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

Ollama llama.cpp LM Studio vLLM

terminal

$ ollama pull ministral-3:8b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run ministral-3:8b

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

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.

03There is room to go to 126K context on this card.

See all models for this rig Compare with another model