Yes — with 27.5 GB to spare

Granite 4.1 30B at Q4_K_M fits your L40S entirely on the GPU at 8K context, at an estimated 32 tokens per second. Past 118K 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 · 16.3 GB Apache 2.0 Released 29 Apr 2026

The largest Granite. Dense 29B at Q4 is a comfortable 24 GB fit.

What hardware do I need for Granite 4.1 30B? →

The VRAM budget

weights 16.3 GB

Weights 16.3 GB KV cache @ 8K 2.00 GB Runtime overhead 0.6 GB Free 27.5 GB of 46.4 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	28.6 GB	31.2 GB	68K	18	−0.1% ppl	Long context
Q6_K	22.1 GB	24.7 GB	94K	24	−0.4% ppl	Long context
Q5_K_M	19.1 GB	21.7 GB	106K	27	−0.8% ppl	Long context
Q4_K_M	16.3 GB	18.9 GB	118K	32	−1.9% ppl	Recommended
Q3_K_M	13.2 GB	15.8 GB	128K	40	−5.4% ppl	Long context
Q2_K	11.3 GB	13.9 GB	128K	46	−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 granite4.1:30b
$ OLLAMA_CONTEXT_LENGTH=8192 \
    ollama run granite4.1:30b

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

01Download is 16.3 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 118K context on this card.

See all models for this rig Compare with another model