What GPU do I need to run intfloat/multilingual-e5-large-instruct?
A 560M-parameter text embedding model. 560M parameters, published in F16. View on Hugging Face
multilingual-e5-large-instruct is published by intfloat on Hugging Face, with 1,420,175 downloads and 641 likes to date. It's a XLMRobertaModel model built for feature-extraction, published natively in F16.
What multilingual-e5-large-instruct is
multilingual-e5-large-instruct is a 560M-parameter embedding model published by intfloat on Hugging Face: it turns text into vectors for search, clustering and retrieval, released under MIT.
License note: permissive: allows commercial use, modification and redistribution. Facts in this section are sourced from multilingual-e5-large-instruct's Hugging Face model card, not benchmarked by Aquanode.
What it's used for
- Semantic search
- Retrieval-augmented generation (RAG)
- Clustering and deduplication
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| FP16 | 1.0 GB | 1.3 GB | V100 | 1 | $0.088/hr |
| FP8 (quantized) | 0.5 GB | 0.6 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 0.3 GB | 0.3 GB | RTX 5060 Ti | 1 | $0.110/hr |
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run multilingual-e5-large-instruct at its published (F16) precision: 1× V100, at $0.088/hr per GPU ($0.088/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
multilingual-e5-large-instruct: common questions
How much VRAM does multilingual-e5-large-instruct need?
1.3 GB at FP16, 0.6 GB at FP8 (quantized), 0.3 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 1.0 GB of weights plus inference overhead is the whole requirement.
How many copies of multilingual-e5-large-instruct fit on one V100?
12, by VRAM alone. That card carries 16.0 GB and one copy needs 1.3 GB at FP16, on a live rate of $0.088/hr for the whole card. Throughput is not modelled here, so 12 copies is not 12 times the requests served.
How to run multilingual-e5-large-instruct
Run multilingual-e5-large-instruct with vLLM
Generic example, not from the model's own docs: adjust flags (quantization, context length, parallelism) for your setup.
vllm serve intfloat/multilingual-e5-large-instruct --task embed --tensor-parallel-size 1Deploy multilingual-e5-large-instruct on Aquanode
Aquanode has no one-click deploy template for multilingual-e5-large-instruct; you install the inference engine yourself with the commands below. Aquanode sells GPU pods billed per second, not a hosted inference API.
- Launch a bare GPU pod sized to the requirement above (1× V100 or larger).
- Open a terminal on the pod, or save one of the commands above as a startup script so it runs automatically the first time the pod boots.
- Run the command and connect to the resulting endpoint.
Launch a GPU podWeight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Related reading: V100 pricing and specs, and The best GPUs for AI, ranked.
