BestLLMfor EN Your hardware. Your LLM. Your call.
APIOpen data Find my LLM
Model fiche

EuroLLM 9B Instruct

By Utter Project / UE · European Union

Updated 2026-07-13

chat general multilingual fr
Parameters
9B
License
Apache 2.0
Context
4k
VRAM (Q4)
6 GB
Released
December 2024

Overview

An EU-funded 9B (Horizon Europe) covering 35 languages including all 24 official EU ones. Trained on 4T tokens on the MareNostrum5 supercomputer and released under Apache 2.0.

When to pick this model

  • You're building EU-focused products that need sovereignty optics
  • You need broad coverage of all 24 official EU languages
  • You want an Apache 2.0 model from a European institution
  • You're working on policy or public-sector projects with EU procurement

VRAM requirements by quantization

VRAM REQUIRED (GB)81216Q4_K_M6 GBQ5_K_M7 GBQ8_010 GBFP1618 GB
QuantizationVRAM required
Q4_K_M (recommended)6 GB
Q5_K_M7 GB
Q8_010 GB
FP16 (no quantization)18 GB

VRAM figures include model weights plus a typical 8k KV cache and ~600 MB runtime overhead (Ollama / llama.cpp baseline). Add headroom for higher context lengths.

In practice, EuroLLM 9B Instruct fits an 8 GB consumer card at Q4_K_M (6 GB). Stepping up to Q8_0 raises the footprint to 10 GB, and unquantized FP16 weights take 18 GB — plan your GPU around the Q4 or Q5 figure unless you specifically need the higher fidelity.

Without a GPU, EuroLLM 9B Instruct needs roughly 12 GB of system RAM to run on CPU via llama.cpp or Ollama — workable for background jobs, but far slower than GPU inference. Throughput estimates from our compatibility engine: around 10 tokens/sec on entry-level GPUs, on the order of 30 tokens/sec on a mid-range card, and up to 80 tokens/sec on high-end hardware — assuming the chosen quantization fully fits in VRAM.

What hardware do you need

The table below matches EuroLLM 9B Instruct to common GPU memory tiers, using the highest-fidelity quantization that fully fits each card class. Spilling layers to system RAM works but costs most of the speed, so size your card to the quantization you actually want to run.

GPU memoryExample cardsBest fit for EuroLLM 9B Instruct
8 GBRTX 5070 Laptop, RTX 5060, RTX 5060 Ti 8GBQ5_K_M (7 GB used)
12 GBRTX 5070, RTX 5070 Ti Laptop, RTX 4080 LaptopQ8_0 (10 GB used)
16 GBRTX 5080, RTX 4080 Super, Radeon RX 9070 XTQ8_0 (10 GB used)
24 GBRTX 4090, Radeon RX 7900 XTX, RTX 5090 LaptopFP16 (18 GB used)
32 GBRTX 5090FP16 (18 GB used)

Which GPU should you buy to run EuroLLM 9B Instruct?

To run EuroLLM 9B Instruct locally at Q4, you need ~6 GB of VRAM. The best value for this is a RTX 5060 (8 GB VRAM).

Check RTX 5060 price on Amazon →

As an Amazon Associate, BestLLMfor earns from qualifying purchases, at no extra cost to you. It does not influence our independent rankings.

Strengths

  • EU sovereignty — Horizon Europe funded
  • Apache 2.0 license
  • Best European open model at its scale
  • Strong coverage of all 24 official EU languages

Limitations

  • Only 4K context — short for modern workloads
  • No official Ollama tag
  • Outpaced by Qwen 3 8B on general benchmarks

Typical workloads

In our catalog grid, EuroLLM 9B Instruct is filed under EU Sovereignty, 24 European Languages — the use cases where its size/quality trade-off makes the most sense. Its tags translate to concrete workloads: multilingual workloads; French-language output where quality matters.

Note the 4k-token context window — fine for short interactions, limiting for long documents or big retrieval contexts. The Apache 2.0 license is permissive, so shipping it inside a commercial product raises no special legal questions.

Architecture & training

Architecture: Dense · 42 layers · GQA (32Q/8KV) · SwiGLU · RoPE · RMSNorm

Training: 4T tokens on MareNostrum5 (BSC). 35 languages (24 EU + extras).

Verdict

The natural pick when EU sovereignty or procurement requires a European-trained Apache 2.0 model.

Quick start

# HuggingFace : utter-project/EuroLLM-9B-Instruct (pas d'Ollama officiel)

Or use the open-source MCP server to query this model from Claude Desktop, Cursor, or any MCP-compatible client.

Similar models worth comparing

Frequently asked questions

How much VRAM does EuroLLM 9B Instruct need?

At the recommended Q4_K_M quantization, EuroLLM 9B Instruct needs about 6 GB of VRAM. Q8_0 takes 10 GB, and unquantized FP16 weights take 18 GB.

Can EuroLLM 9B Instruct run without a GPU?

Yes — with roughly 12 GB of system RAM it runs CPU-only through llama.cpp or Ollama. Expect a fraction of GPU speed, which is fine for background or batch jobs but slow for interactive chat.

What context window does EuroLLM 9B Instruct support?

EuroLLM 9B Instruct supports a 4k-token context window (4,096 tokens).

Can I use EuroLLM 9B Instruct commercially?

Yes. EuroLLM 9B Instruct is released under Apache 2.0, a permissive open-source license that allows commercial use, modification and redistribution.

How fast is EuroLLM 9B Instruct on consumer hardware?

Our compatibility engine estimates on the order of 30 tokens/sec on a mid-range GPU and up to 80 tokens/sec on high-end cards, assuming the quantization fully fits in VRAM.

Which quantization of EuroLLM 9B Instruct should I download first?

Start with Q4_K_M (6 GB) — the standard size/quality sweet spot. Step up to Q5_K_M or Q8_0 only if you have VRAM headroom. It already fits an 8 GB card at Q5_K_M.

Tools

Is EuroLLM 9B Instruct the right pick for you?

Compute self-hosted ROI → Back to catalog